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

    Neuronpedia

    INDEX
    Explanations

    interested in explosives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Voice
    0.46
    ya
    0.45
    ff
    0.44
    $+
    0.43
    Correo
    0.43
    Market
    0.43
    c
    0.43
    Anything
    0.42
    Could
    0.42
    בין
    0.41
    POSITIVE LOGITS
     Basement
    0.52
    arıyla
    0.52
     profond
    0.49
     wypeł
    0.48
     zodat
    0.47
    プレイヤー
    0.47
    ീഷ
    0.46
     materia
    0.44
     encrypt
    0.44
     keratin
    0.43
    Act Density 0.002%

    No Known Activations