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

    Neuronpedia

    INDEX
    Explanations

    your

    np_max-act · gemini-2.0-flash

    The neuron activates on instances of the word “help,” i.e. when the text is requesting or referring to assistance.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ▼
    -0.07
     groupName
    -0.07
     плани
    -0.06
    /met
    -0.06
     dosy
    -0.06
    %s
    -0.06
     Honor
    -0.06
     beurette
    -0.06
    _choose
    -0.06
     ของ
    -0.06
    POSITIVE LOGITS
     Aeros
    0.08
    131
    0.07
    (bounds
    0.07
    疫
    0.07
    orea
    0.06
    _bid
    0.06
    ông
    0.06
    (topic
    0.06
    TRACT
    0.06
    ydro
    0.06
    Act Density 0.007%

    No Known Activations