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

    Neuronpedia

    INDEX
    Explanations

    80

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _cell
    -0.07
     Kak
    -0.06
    .cpp
    -0.06
    .box
    -0.06
    ुम
    -0.06
    _apply
    -0.06
     supervise
    -0.06
     unquestion
    -0.06
    SOAP
    -0.06
     blindness
    -0.06
    POSITIVE LOGITS
     �
    0.07
    OPT
    0.07
    bb
    0.07
    ریق
    0.07
    نسا
    0.07
     NSTextAlignment
    0.06
     nive
    0.06
     праці
    0.06
    American
    0.06
     ника
    0.06
    Act Density 0.001%

    No Known Activations