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

    Neuronpedia

    INDEX
    Explanations

    be less

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    usive
    0.40
     dispositions
    0.39
    dummy
    0.38
     left
    0.38
     Bomb
    0.37
    left
    0.36
    ള്ള
    0.36
     libertad
    0.36
    Left
    0.36
    vere
    0.35
    POSITIVE LOGITS
    냐면
    0.41
     vértice
    0.39
    Escolhido
    0.39
     Лука
    0.38
    Ner
    0.38
    ᴼ
    0.38
     koa
    0.37
    MovieModal
    0.37
    ܵ
    0.37
     hand
    0.36
    Act Density 0.000%

    No Known Activations