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

    Neuronpedia

    INDEX
    Explanations

    events and organizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     resp
    -0.07
     Kore
    -0.07
     teor
    -0.06
     alunos
    -0.06
     hooks
    -0.06
     lub
    -0.06
     خد
    -0.06
     ambitions
    -0.06
     lesbians
    -0.06
     drunk
    -0.06
    POSITIVE LOGITS
    .getItemId
    0.07
    wm
    0.07
    Fmt
    0.07
    cript
    0.07
    .platform
    0.06
    .cljs
    0.06
    ských
    0.06
    ña
    0.06
    lif
    0.06
    уществ
    0.06
    Act Density 0.101%

    No Known Activations