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

    Neuronpedia

    INDEX
    Explanations

    smile

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     confusing
    -0.07
     Femin
    -0.06
    /logs
    -0.06
    .lifecycle
    -0.06
    kte
    -0.06
     Behaviour
    -0.06
     mission
    -0.06
     Μετα
    -0.06
     False
    -0.06
     усл
    -0.06
    POSITIVE LOGITS
    past
    0.07
    xmlns
    0.07
     Kanunu
    0.07
     NK
    0.06
    seen
    0.06
    .DataGridViewTextBoxColumn
    0.06
    _nil
    0.06
     gar
    0.06
    rem
    0.06
     xmlns
    0.06
    Act Density 0.013%

    No Known Activations