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

    Neuronpedia

    INDEX
    Explanations

    say }

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Num
    -0.07
    ��
    -0.06
    lam
    -0.06
    CustomerId
    -0.06
    _Ex
    -0.06
    nung
    -0.06
    液
    -0.06
    azel
    -0.06
    oten
    -0.06
    Fd
    -0.06
    POSITIVE LOGITS
     เส
    0.07
    ونه
    0.06
     Couples
    0.06
     landlord
    0.06
     групп
    0.06
    цез
    0.06
    \Log
    0.06
     }}</
    0.06
    _MODAL
    0.06
     complet
    0.06
    Act Density 0.025%

    No Known Activations