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

    Neuronpedia

    INDEX
    Explanations

    under

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Contractor
    -0.07
    $max
    -0.06
     ETA
    -0.06
    iterals
    -0.06
     Historic
    -0.06
     رسمی
    -0.06
    _notify
    -0.06
     عمل
    -0.06
     Mature
    -0.06
    коп
    -0.06
    POSITIVE LOGITS
    ağ
    0.07
     �
    0.07
     disciples
    0.06
     üz
    0.06
     troubles
    0.06
     revers
    0.06
     underwater
    0.06
     sob
    0.06
     هوش
    0.06
     обст
    0.06
    Act Density 0.012%

    No Known Activations