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

    Neuronpedia

    INDEX
    Explanations

    string manipulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    爫
    0.45
     تبع
    0.44
     Tjiwarl
    0.44
    ♕
    0.42
     valv
    0.42
    WithFieldContext
    0.42
    ulfate
    0.41
     treasury
    0.41
     налого
    0.41
     cubo
    0.40
    POSITIVE LOGITS
     substrings
    1.68
     substring
    1.64
     string
    1.62
    字符串
    1.60
    substring
    1.47
     strlen
    1.44
    Substring
    1.42
     strings
    1.40
    string
    1.34
     String
    1.34
    Act Density 0.100%

    No Known Activations