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

    Neuronpedia

    INDEX
    Explanations

    common phrases and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fonseca
    0.41
     restoring
    0.40
     clashes
    0.39
     clout
    0.39
     Vote
    0.37
     ক্যান্ট
    0.36
    WithOwner
    0.36
     ought
    0.35
     reviving
    0.35
     formatting
    0.35
    POSITIVE LOGITS
     लाहि
    0.45
     alvo
    0.38
    ̳
    0.38
    average
    0.38
    诀
    0.38
    std
    0.38
    白
    0.37
    ӗ
    0.37
    ウィ
    0.36
     blanca
    0.36
    Act Density 0.000%

    No Known Activations