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

    Neuronpedia

    INDEX
    Explanations

    personal feelings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Petit
    -0.07
     значение
    -0.06
    Rotate
    -0.06
    Вы
    -0.06
    Cri
    -0.06
    );↵↵↵↵
    -0.06
    ;-
    -0.06
    .questions
    -0.06
    _DYNAMIC
    -0.06
    тон
    -0.06
    POSITIVE LOGITS
    的真实性
    0.07
    publication
    0.07
     ingress
    0.07
     evidenced
    0.07
    affles
    0.07
     огр
    0.07
    ばかり
    0.07
    لزم
    0.07
    (separator
    0.07
    Browsable
    0.07
    Act Density 0.004%

    No Known Activations