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

    Neuronpedia

    INDEX
    Explanations

    two boys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ferrugineux
    0.61
     arabe
    0.61
     Vestone
    0.58
     épaisse
    0.57
     comptes
    0.55
     sonore
    0.55
    метров
    0.55
     aldı
    0.54
     Obrigado
    0.54
    ことができる
    0.53
    POSITIVE LOGITS
    I
    0.63
    matching
    0.54
    list
    0.54
    ai
    0.53
    صة
    0.52
    C
    0.49
    tol
    0.49
     been
    0.47
    been
    0.47
    W
    0.47
    Act Density 0.000%

    No Known Activations