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

    Neuronpedia

    INDEX
    Explanations

    names starting with S

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    利
    0.38
    ="#{
    0.37
    yst
    0.37
    вут
    0.37
     ریکارڈ
    0.36
     prototypes
    0.36
    chars
    0.35
     effectuer
    0.35
    ૬
    0.35
    ldquo
    0.35
    POSITIVE LOGITS
    に伴
    0.38
    の子
    0.38
     goose
    0.37
     Wolfram
    0.36
     वडिला
    0.35
    ແ
    0.35
     Raman
    0.34
     blod
    0.34
    𒀊
    0.34
     ജ
    0.34
    Act Density 0.001%

    No Known Activations