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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .DataGridViewColumn
    -0.06
    ToDo
    -0.06
    assistant
    -0.06
     cunning
    -0.06
    Islam
    -0.06
    .execSQL
    -0.06
    лоп
    -0.06
     Groups
    -0.06
     Theresa
    -0.06
    _snapshot
    -0.06
    POSITIVE LOGITS
    caa
    0.07
    ısında
    0.07
    iverz
    0.06
     DataTable
    0.06
    ávání
    0.06
    ová
    0.06
     critics
    0.06
    lemek
    0.06
    イ
    0.06
    anova
    0.06
    Act Density 0.088%

    No Known Activations