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

    Neuronpedia

    INDEX
    Explanations

    lists of people

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     consid
    -0.07
     Best
    -0.07
     setActive
    -0.07
     bullpen
    -0.07
    .navigator
    -0.06
     '@/
    -0.06
     Interrupt
    -0.06
     المو
    -0.06
     ancestor
    -0.06
    _CRITICAL
    -0.06
    POSITIVE LOGITS
     ho
    0.07
    ��
    0.07
     suma
    0.06
    耶
    0.06
     rocked
    0.06
     actividad
    0.06
     multis
    0.06
    loss
    0.06
     Allow
    0.06
    ovým
    0.06
    Act Density 0.016%

    No Known Activations