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

    Neuronpedia

    INDEX
    Explanations

    legal discovery

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    icals
    -0.06
     unr
    -0.06
     pari
    -0.06
     deze
    -0.06
    lass
    -0.06
    qed
    -0.06
     consc
    -0.06
     puesto
    -0.06
    *n
    -0.06
     mı
    -0.06
    POSITIVE LOGITS
     Erect
    0.07
     Manny
    0.06
    _HEAP
    0.06
    regular
    0.06
     законодав
    0.06
     голов
    0.06
    .Month
    0.06
     ang
    0.06
     Особ
    0.06
     sexual
    0.06
    Act Density 0.026%

    No Known Activations