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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     looming
    -0.07
     rhyme
    -0.07
     Lyrics
    -0.06
    �
    -0.06
     　 　
    -0.06
    だろう
    -0.06
     fraud
    -0.06
    　 　
    -0.06
    Gram
    -0.06
     jeder
    -0.06
    POSITIVE LOGITS
     Character
    0.07
    MSN
    0.07
    /Observable
    0.07
    character
    0.07
    ορειο
    0.07
    echan
    0.06
     prizes
    0.06
     فایل
    0.06
    .Transform
    0.06
     Parts
    0.06
    Act Density 0.017%

    No Known Activations