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

    Neuronpedia

    INDEX
    Explanations

    complex topics and situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    V
    0.62
     ಡಿ
    0.55
    َ
    0.54
    y
    0.53
     majeur
    0.52
    a
    0.52
    an
    0.49
    Vic
    0.48
     a
    0.48
    й
    0.48
    POSITIVE LOGITS
     situaciones
    0.79
     situación
    0.75
     situações
    0.70
    事が
    0.69
     situação
    0.67
     Некоторые
    0.64
     situazione
    0.64
    牞
    0.64
     operadores
    0.63
    了几
    0.62
    Act Density 0.000%

    No Known Activations