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

    Neuronpedia

    INDEX
    Explanations

    appliances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    д
    1.82
    то
    1.59
    ти
    1.42
    на
    1.36
    м
    1.35
    de
    1.34
     vực
    1.26
    "$
    1.23
    ro
    1.21
    saturated
    1.20
    POSITIVE LOGITS
    ్వ
    1.49
     Lakewood
    1.36
     SLAs
    1.31
     doré
    1.31
    umably
    1.28
    ooo
    1.28
    ческих
    1.28
     lưng
    1.26
    myLabels
    1.25
    高校
    1.25
    Act Density 0.001%

    No Known Activations