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

    Neuronpedia

    INDEX
    Explanations

    prime example, source, suspect, candidate, target

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    S
    0.91
    g
    0.89
    X
    0.76
    q
    0.74
    P
    0.73
    r
    0.72
    h
    0.71
    w
    0.68
    j
    0.68
    si
    0.66
    POSITIVE LOGITS
     точке
    0.77
     vantage
    0.76
     месте
    0.74
     குறித்து
    0.69
     четвер
    0.66
    めに
    0.66
     благоприят
    0.66
     👌
    0.66
     условия
    0.65
    iary
    0.64
    Act Density 0.020%

    No Known Activations