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

    Neuronpedia

    INDEX
    Explanations

    same, identical, similar, consistent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     active
    0.82
     aktif
    0.77
    Active
    0.75
     estimados
    0.75
     añadió
    0.74
     Active
    0.72
    active
    0.72
     dépasse
    0.71
    Der
    0.69
     ativa
    0.68
    POSITIVE LOGITS
    相同的
    1.46
     identical
    1.44
    共通
    1.27
    identical
    1.20
     similarities
    1.20
     одина
    1.19
    同一
    1.18
     uniform
    1.17
     same
    1.17
    相同
    1.16
    Act Density 1.738%

    No Known Activations