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

    Neuronpedia

    INDEX
    Explanations

    minimum required

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     싶
    1.31
    ১
    1.30
    ,\,
    1.27
    ることができます
    1.24
    れて
    1.22
     примере
    1.20
    Keefe
    1.20
    প্রিল
    1.20
    possible
    1.19
    [
    1.19
    POSITIVE LOGITS
    臾
    1.83
     evil
    1.73
     evils
    1.67
    ArgsConstructor
    1.64
    tyn
    1.59
    стью
    1.56
    𝒚
    1.54
    不然
    1.50
     minimum
    1.45
     Evil
    1.40
    Act Density 0.113%

    No Known Activations