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

    Neuronpedia

    INDEX
    Explanations

    keeping track

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ''''
    0.67
    habitation
    0.66
    likle
    0.66
     It
    0.65
    You
    0.65
    iin
    0.65
    𝘳
    0.64
    insect
    0.64
    र्घ
    0.63
    ।.
    0.63
    POSITIVE LOGITS
     of
    0.92
    ท
    0.80
    에
    0.79
     C
    0.73
    ست
    0.73
    си
    0.72
    ен
    0.70
    ט
    0.69
     T
    0.68
    ات
    0.66
    Act Density 0.001%

    No Known Activations