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

    Neuronpedia

    INDEX
    Explanations

    Formal Language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atemala
    -0.07
    oundary
    -0.07
    №
    -0.06
    forget
    -0.06
    <![
    -0.06
     tennis
    -0.06
     FIRST
    -0.06
    Boot
    -0.06
    .tt
    -0.06
     готов
    -0.06
    POSITIVE LOGITS
    افی
    0.07
    extAlignment
    0.07
    altung
    0.06
     disarm
    0.06
    ckså
    0.06
     آبی
    0.06
    _ABORT
    0.06
     لل
    0.06
    _BOTH
    0.06
    LARI
    0.06
    Act Density 0.393%

    No Known Activations