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

    Neuronpedia

    INDEX
    Explanations

    Code/quizzes/interviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nuovo
    -0.07
     vegan
    -0.07
     uč
    -0.06
     compete
    -0.06
    .Results
    -0.06
    _ticket
    -0.06
     treaties
    -0.06
     Artikel
    -0.06
    /new
    -0.06
     ingl
    -0.06
    POSITIVE LOGITS
     RESP
    0.08
    Jacob
    0.07
     OBS
    0.07
     ipAddress
    0.07
     Anonymous
    0.07
     BR
    0.06
    ่าอ
    0.06
    closest
    0.06
     PTR
    0.06
    selling
    0.06
    Act Density 0.157%

    No Known Activations