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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fração
    0.87
    mfrac
    0.87
    frac
    0.83
     theta
    0.81
     fraction
    0.77
     fracción
    0.76
    0.75
     Ψ
    0.75
    ӡ
    0.72
    0.72
    POSITIVE LOGITS
    cap
    0.76
     supp
    0.72
    सेट
    0.64
    Cap
    0.64
     cap
    0.64
     연
    0.64
    blind
    0.62
     হৃদ
    0.62
    col
    0.61
    ᄋ
    0.60
    Act Density 0.010%

    No Known Activations