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

    Neuronpedia

    INDEX
    Explanations

    Forgetting or something negative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     forget
    -0.68
    AndEndTag
    -0.65
    er
    -0.63
     fuck
    -0.60
    ixer
    -0.60
     sucks
    -0.56
    RenderAtEndOf
    -0.56
     sniffing
    -0.56
    suck
    -0.55
     smells
    -0.54
    POSITIVE LOGITS
    IndentedString
    0.65
     autorytatywna
    0.63
    GraphicsUnit
    0.59
    rungsseite
    0.56
    хьтан
    0.53
     Autorizaciones
    0.50
    IANGLES
    0.49
    Демографія
    0.49
    VIAF
    0.48
    odil
    0.48
    Act Density 0.047%

    No Known Activations