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

    Neuronpedia

    INDEX
    Explanations

    string manipulation and data types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    elines
    0.41
    estre
    0.41
    culaire
    0.40
    )
    0.39
    fé
    0.39
    )..
    0.38
    agon
    0.38
    urity
    0.38
    )}>
    0.38
    )}]{
    0.36
    POSITIVE LOGITS
    AsFactors
    0.63
    fromCharCode
    0.51
    ByAppending
    0.51
    Tokenizer
    0.48
    ית
    0.48
    representation
    0.48
    ifies
    0.47
    ﹁
    0.47
    Length
    0.47
     string
    0.47
    Act Density 0.023%

    No Known Activations