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

    Neuronpedia

    INDEX
    Explanations

    Nature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pawn
    -0.07
    教
    -0.07
     socially
    -0.06
    ?,?,
    -0.06
     cruising
    -0.06
     intolerance
    -0.06
    ولو
    -0.06
    गर
    -0.06
     Florence
    -0.06
     соци
    -0.06
    POSITIVE LOGITS
     Nature
    0.07
    вед
    0.07
     půj
    0.07
    scaled
    0.06
    かな
    0.06
    撤
    0.06
    lh
    0.06
    __("
    0.06
     Tanrı
    0.06
     createUser
    0.06
    Act Density 0.001%

    No Known Activations