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

    Neuronpedia

    INDEX
    Explanations

    research publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     isi
    -0.07
    Artifact
    -0.07
    626
    -0.06
     aluno
    -0.06
     Agreement
    -0.06
    езд
    -0.06
    ρώ
    -0.06
    umsuz
    -0.06
    ceans
    -0.06
    unken
    -0.06
    POSITIVE LOGITS
    _confirmation
    0.08
    _TICK
    0.07
    ा
    0.06
    .Graph
    0.06
    :"",
    0.06
    /component
    0.06
     Schw
    0.06
     TForm
    0.06
     viết
    0.06
    'nda
    0.06
    Act Density 0.041%

    No Known Activations