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

    Neuronpedia

    INDEX
    Explanations

    technical/scientific texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SW
    -0.06
     LGBTQ
    -0.06
    Ст
    -0.06
     卡
    -0.06
    jez
    -0.06
     disclosure
    -0.06
    �
    -0.06
     Peg
    -0.05
     мінім
    -0.05
    peq
    -0.05
    POSITIVE LOGITS
    .persistence
    0.07
     Potato
    0.07
     uží
    0.07
     jelly
    0.06
    .Are
    0.06
     legitimately
    0.06
    antaged
    0.06
    .setColumns
    0.06
    .Concat
    0.06
    _VOID
    0.06
    Act Density 0.307%

    No Known Activations