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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    щення
    -0.07
     Drive
    -0.07
    箱
    -0.07
    _STENCIL
    -0.06
    �
    -0.06
    xBD
    -0.06
     Sunny
    -0.06
    FIN
    -0.06
    (js
    -0.06
    ��이
    -0.06
    POSITIVE LOGITS
     ＞
    0.07
    olph
    0.07
    .comments
    0.06
    =this
    0.06
     sondern
    0.06
     sklearn
    0.06
    dık
    0.06
    _Mouse
    0.06
     odio
    0.06
    ig
    0.06
    Act Density 0.028%

    No Known Activations