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

    Neuronpedia

    INDEX
    Explanations

    JSONPlaceholder, unlock, newbie, Homebrew, disapprove

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1.54
    ing
    1.25
     a
    1.15
    s
    1.11
    I
    1.10
     I
    1.02
    à
    0.96
    al
    0.91
    ile
    0.88
     (
    0.84
    POSITIVE LOGITS
    newtheorem
    1.25
    з
    1.11
    خ
    1.07
    н
    1.00
    م
    0.98
    ب
    0.98
     границ
    0.96
    ות
    0.93
     родился
    0.88
    р
    0.87
    Act Density 0.000%

    No Known Activations