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

    Neuronpedia

    INDEX
    Explanations

    APP followed by numbers or "and"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    0.71
    s
    0.67
     as
    0.64
    ের
    0.64
    ی
    0.62
    l
    0.58
     chama
    0.57
     deprecated
    0.55
     oscill
    0.52
     Marse
    0.52
    POSITIVE LOGITS
    팅
    0.48
    雹
    0.48
    高端
    0.46
    মণ্ড
    0.46
    awing
    0.46
     राह
    0.46
     एक्
    0.45
    صرية
    0.44
    田
    0.44
     मिळ
    0.44
    Act Density 0.000%

    No Known Activations