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

    Neuronpedia

    INDEX
    Explanations

    use affirmative or objective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    0.71
    盾
    0.50
    িকে
    0.50
    ꔰ
    0.49
    ת
    0.48
    yó
    0.48
    كتب
    0.47
    다
    0.47
    Honestly
    0.46
    をお
    0.46
    POSITIVE LOGITS
     Falcons
    0.48
     seres
    0.46
    avad
    0.46
     Gord
    0.45
    accharides
    0.44
     chats
    0.44
     극한
    0.44
    umed
    0.43
    ac
    0.43
    atians
    0.43
    Act Density 0.000%

    No Known Activations