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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }">
    0.89
    E
    0.89
    {
    0.85
    "
    0.83
    C
    0.77
    D
    0.77
    ach
    0.76
    (
    0.76
    A
    0.76
    M
    0.76
    POSITIVE LOGITS
    treme
    0.86
    ма
    0.79
    я
    0.77
    তে
    0.75
     veya
    0.73
    ש
    0.72
    ército
    0.69
    ด
    0.67
    avier
    0.65
    μα
    0.64
    Act Density 0.963%

    No Known Activations