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

    Neuronpedia

    INDEX
    Explanations

    Measurements and distances

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aj
    -0.07
     Gree
    -0.06
    Knight
    -0.06
    Metal
    -0.06
    .mount
    -0.06
     Che
    -0.06
     порядку
    -0.06
    距
    -0.06
    मह
    -0.06
    ので
    -0.06
    POSITIVE LOGITS
     distractions
    0.07
     reinstall
    0.07
    (question
    0.07
    ENN
    0.06
    ».
    0.06
     reconnaissance
    0.06
     trabalho
    0.06
    gte
    0.06
    .unshift
    0.06
    .nextLine
    0.06
    Act Density 0.007%

    No Known Activations