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

    Neuronpedia

    INDEX
    Explanations

    ig

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .")
    -0.07
     execution
    -0.06
    ::::::::::::::
    -0.06
     dinner
    -0.06
     =================================================
    -0.06
     Baker
    -0.06
    ()+"
    -0.06
    _traffic
    -0.06
     ====
    -0.06
     zaten
    -0.06
    POSITIVE LOGITS
     competitive
    0.06
    _AL
    0.06
     quantidade
    0.06
     زیست
    0.06
    (hist
    0.06
    .ins
    0.06
    :inline
    0.06
    miş
    0.06
    uido
    0.06
     distinguishing
    0.06
    Act Density 0.003%

    No Known Activations