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

    Neuronpedia

    INDEX
    Explanations

    en

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _REFRESH
    -0.07
     birkaç
    -0.07
     REL
    -0.06
     kepada
    -0.06
     negate
    -0.06
     Burada
    -0.06
     světě
    -0.06
     Thick
    -0.06
     metav
    -0.06
    Lock
    -0.06
    POSITIVE LOGITS
    .en
    0.07
    َر
    0.06
     colon
    0.06
    gren
    0.06
    Editing
    0.06
    ヾ
    0.06
     padding
    0.06
    ,tr
    0.06
     точки
    0.06
    ued
    0.06
    Act Density 0.008%

    No Known Activations