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

    Neuronpedia

    INDEX
    Explanations

    ray and shark comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    0.56
     Edward
    0.55
     Law
    0.54
    ’
    0.52
     $€
    0.52
    سم
    0.50
     Odysseus
    0.49
     Athens
    0.48
     Earl
    0.48
     Optim
    0.48
    POSITIVE LOGITS
     exposición
    0.62
    Amplitude
    0.58
     batería
    0.55
    Institut
    0.55
    ಾಪ
    0.54
     மில்லியன்
    0.53
    Evento
    0.53
    िकुलम
    0.53
    ᅮ
    0.53
    वियस
    0.52
    Act Density 0.000%

    No Known Activations