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

    Neuronpedia

    INDEX
    Explanations

    commit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    まる
    -0.07
    Chocolate
    -0.06
    стати
    -0.06
    something
    -0.06
    кид
    -0.06
     �
    -0.06
     Bracket
    -0.06
     endangered
    -0.06
    Despite
    -0.06
    는데
    -0.06
    POSITIVE LOGITS
     ACA
    0.06
     sg
    0.06
    lator
    0.06
    _chat
    0.06
     previously
    0.06
     mluv
    0.06
     Talent
    0.06
     파
    0.06
    .Sql
    0.06
     SMS
    0.06
    Act Density 0.022%

    No Known Activations