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

    Neuronpedia

    INDEX
    Explanations

    concept of secret

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Innocent
    0.47
     Buscar
    0.45
     Zag
    0.45
     accented
    0.44
     заб
    0.43
     Blanch
    0.42
     ausencia
    0.42
     Ale
    0.41
    ாச
    0.40
     consolidated
    0.40
    POSITIVE LOGITS
     secret
    1.23
    secret
    1.21
     비밀
    1.13
     секре
    1.09
    secrets
    1.09
     secreto
    1.09
    Secret
    1.07
    秘密
    1.05
     secretos
    1.03
     secrets
    1.02
    Act Density 0.023%

    No Known Activations