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

    Neuronpedia

    INDEX
    Explanations

    descriptions of people arriving or entering a scene

    oai_token-act-pair · gemini-2.0-flash

    opening doors/knocks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ValueGenerated
    -0.57
    tr
    -0.49
    ThroughAttribute
    -0.49
    !
    -0.47
    FieldDescriptor
    -0.47
    matchCondition
    -0.46
    ีก
    -0.46
    ross
    -0.45
    сп
    -0.45
    con
    -0.44
    POSITIVE LOGITS
     tartalomajánló
    0.73
     myſelf
    0.73
     يتيمه
    0.72
    ſelf
    0.67
     Eſ
    0.64
    twimg
    0.64
     سكانية
    0.63
     الحره
    0.63
     themſelves
    0.62
     itſelf
    0.62
    Act Density 1.105%

    No Known Activations