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

    Neuronpedia

    INDEX
    Explanations

    miscellaneous text snippets

    np_max-act · gemini-2.0-flash

    The neuron activates on English words ending in “-ing,” i.e. gerunds or present-participle forms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     mà
    -0.06
    -negative
    -0.06
    "]]
    -0.06
     miền
    -0.06
     провер
    -0.06
     che
    -0.06
     traumat
    -0.06
    “What
    -0.06
     CPA
    -0.06
    which
    -0.06
    POSITIVE LOGITS
     Про
    0.07
    099
    0.07
    \uC
    0.07
     carte
    0.06
     besch
    0.06
     Anast
    0.06
    Into
    0.06
    .ArgumentParser
    0.06
     SQLException
    0.06
    #aa
    0.06
    Act Density 0.459%

    No Known Activations