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

    Neuronpedia

    INDEX
    Explanations

    the secret

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     opined
    0.50
     endeavoured
    0.49
     열심히
    0.48
     endeav
    0.47
     consummate
    0.47
     നന്ന
    0.47
    üglich
    0.46
     endeavors
    0.46
    いろいろ
    0.46
     morphism
    0.46
    POSITIVE LOGITS
     secret
    0.73
    secret
    0.71
    SECRET
    0.68
    秘密
    0.66
     secreto
    0.66
     secretly
    0.65
     secretos
    0.62
     Secret
    0.61
     proven
    0.60
     SECRET
    0.59
    Act Density 0.026%

    No Known Activations