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

    Neuronpedia

    INDEX
    Explanations

    harmful code or lethal injection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    planilla
    0.52
    faktor
    0.51
    factor
    0.51
    ivasena
    0.51
    objeto
    0.50
     variado
    0.50
     نجي
    0.50
    multiply
    0.50
    tidy
    0.50
    ഗ്രഹ
    0.50
    POSITIVE LOGITS
    ’
    0.55
    ↵
    0.50
    '
    0.50
     Stickers
    0.47
     is
    0.46
     or
    0.44
     where
    0.44
    ↵↵
    0.44
     prizes
    0.44
    问
    0.43
    Act Density 0.000%

    No Known Activations