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

    Neuronpedia

    INDEX
    Explanations

    optional, voluntary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    amis
    0.42
     चुकी
    0.40
     ആയ
    0.39
    とにかく
    0.38
     подрост
    0.38
    독
    0.37
     devaluation
    0.37
     nedost
    0.36
    早く
    0.36
     სწ
    0.36
    POSITIVE LOGITS
     optional
    1.94
    optional
    1.80
    Optional
    1.73
     Optional
    1.73
     optionally
    1.43
    可选
    1.32
     Optionally
    1.19
     voluntary
    1.14
     वैकल्पिक
    1.04
     voluntarily
    1.03
    Act Density 0.219%

    No Known Activations