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

    Neuronpedia

    INDEX
    Explanations

    technical units and measures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ent
    0.90
    Ent
    0.71
     Acting
    0.70
     ENT
    0.69
    lą
    0.69
     Einst
    0.68
     हिट
    0.67
     entree
    0.65
     적극
    0.65
     básicos
    0.65
    POSITIVE LOGITS
    float
    0.88
    aps
    0.80
    tw
    0.79
     tw
    0.79
    Float
    0.79
    amsmath
    0.78
    amsfonts
    0.76
    prd
    0.74
     floats
    0.74
     float
    0.72
    Act Density 0.117%

    No Known Activations