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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .VideoCapture
    -0.07
    часно
    -0.07
     CIS
    -0.07
     amb
    -0.07
    ییر
    -0.07
     Dungeon
    -0.06
     kategor
    -0.06
     Dum
    -0.06
    مة
    -0.06
     gently
    -0.06
    POSITIVE LOGITS
     since
    0.08
     ww
    0.07
    SY
    0.07
     FDA
    0.06
    rad
    0.06
     railing
    0.06
     Knowledge
    0.06
     Firearms
    0.06
    _gt
    0.06
    olve
    0.06
    Act Density 0.003%

    No Known Activations