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

    Neuronpedia

    INDEX
    Explanations

    string conversion and manipulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Percolation
    0.72
     Liste
    0.66
     Fatigue
    0.65
     Alors
    0.65
     copied
    0.64
    aní
    0.63
     seven
    0.63
     Epile
    0.63
     cursed
    0.63
     צו
    0.62
    POSITIVE LOGITS
    trim
    0.83
    Convert
    0.82
    Escape
    0.81
     convert
    0.81
    Converting
    0.80
     converting
    0.79
    Trim
    0.78
    escape
    0.78
     sanitize
    0.76
     converts
    0.74
    Act Density 0.033%

    No Known Activations