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

    Neuronpedia

    INDEX
    Explanations

    Kir, Kira, Keira, Quirós

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ске
    0.92
     looping
    0.86
    fonction
    0.78
     head
    0.77
     unbounded
    0.75
    рость
    0.74
    瞼
    0.74
    itious
    0.73
    魇
    0.73
     पादुकोण
    0.73
    POSITIVE LOGITS
    p
    0.80
    ullahi
    0.78
    textContent
    0.76
    Typography
    0.75
    text
    0.74
    PlayerSelector
    0.72
    𝙩
    0.71
    texts
    0.71
    𝙜
    0.71
     કર
    0.71
    Act Density 0.100%

    No Known Activations