Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    k

    np_max-act · gemini-2.0-flash

    statistics and numerical data related to web traffic and performance.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on numeric quantities in the thousands—i.e. numbers written with a “K” or “k” suffix (e.g. “10 K,” “50 K,” “100k”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     pseud
    -0.07
     для
    -0.07
     xảy
    -0.07
     deutschen
    -0.07
    hour
    -0.07
     edildi
    -0.07
     приня
    -0.07
    .putString
    -0.07
    純
    -0.07
     thirteen
    -0.07
    POSITIVE LOGITS
     kicks
    0.06
     conduct
    0.06
    I
    0.06
    FetchRequest
    0.06
    _ASSOC
    0.06
    技
    0.06
    Mesh
    0.06
     flock
    0.06
            
↵
    0.05
     marvel
    0.05
    Act Density 0.010%

    No Known Activations