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

    Neuronpedia

    INDEX
    Explanations

    Descriptive text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    278
    -0.07
    КИ
    -0.07
    BLACK
    -0.06
     bpy
    -0.06
    780
    -0.06
     fg
    -0.06
    "C
    -0.06
     freak
    -0.06
     Wheeler
    -0.06
    lena
    -0.06
    POSITIVE LOGITS
     Grants
    0.07
    ód
    0.06
     cigarette
    0.06
    ................
    0.06
    _detected
    0.06
     Indians
    0.06
    leşme
    0.06
    inesis
    0.06
    .***.***
    0.06
     phon
    0.06
    Act Density 0.045%

    No Known Activations