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

    Neuronpedia

    INDEX
    Explanations

    Swift code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     نفسه
    0.86
    Replace
    0.82
    自己
    0.77
    replace
    0.76
    Belle
    0.75
     ourselves
    0.74
    ///
    0.74
     نفسها
    0.73
    tags
    0.73
    PRINT
    0.67
    POSITIVE LOGITS
     बराम
    0.87
     ϕ
    0.86
    ανο
    0.78
     transmitter
    0.77
     transmission
    0.77
     eslint
    0.76
     exhibition
    0.76
    ρύ
    0.76
    anders
    0.75
     pathology
    0.74
    Act Density 0.002%

    No Known Activations