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

    Neuronpedia

    INDEX
    Explanations

    secret key configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arranged
    0.44
     ভাঙ
    0.42
     biotic
    0.41
    arranged
    0.40
     begged
    0.40
     down
    0.38
     unnatural
    0.38
     advanced
    0.38
     onChanged
    0.37
     warehouse
    0.37
    POSITIVE LOGITS
    Secret
    0.55
     Secret
    0.51
     SECRET
    0.51
     secreto
    0.48
     secret
    0.45
     секре
    0.45
    SECRET
    0.44
     কবি
    0.42
     вокруг
    0.42
    秘
    0.39
    Act Density 0.006%

    No Known Activations