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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ATAB
    -0.07
    chartInstance
    -0.06
     yeşil
    -0.06
    ページ
    -0.06
    Descri
    -0.06
     Coy
    -0.06
     mužů
    -0.06
     Calcul
    -0.06
    03
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    phones
    0.07
     πιο
    0.06
     wanted
    0.06
    _COMBO
    0.06
     ethos
    0.06
    ующие
    0.06
    /owl
    0.06
    石
    0.06
    Detect
    0.06
     Bonus
    0.06
    Act Density 0.017%

    No Known Activations