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

    Neuronpedia

    INDEX
    Explanations

    laws related to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.38
     radically
    0.38
    .
    0.34
    the
    0.34
    ↵
    0.31
    more
    0.29
     vastly
    0.29
     richly
    0.29
    his
    0.29
    mě
    0.29
    POSITIVE LOGITS
     यह
    0.49
    このような
    0.45
     এই
    0.44
     এইরূপ
    0.43
    📢
    0.42
    對於
    0.42
    是因為
    0.41
     dieser
    0.41
    名稱
    0.39
    ennzeichnet
    0.39
    Act Density 0.078%

    No Known Activations