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

    Neuronpedia

    INDEX
    Explanations

    questionnaires and scoring

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gzip
    -0.06
    ई
    -0.06
     پی
    -0.06
     Lif
    -0.06
    CTest
    -0.06
    Ub
    -0.06
     маг
    -0.06
    .flip
    -0.06
    PS
    -0.06
    masters
    -0.06
    POSITIVE LOGITS
     herkes
    0.07
     Savaş
    0.07
    様
    0.06
    ocumented
    0.06
    uing
    0.06
     orchestrated
    0.06
    \Queue
    0.06
     Snapshot
    0.06
    oom
    0.06
    acak
    0.06
    Act Density 0.011%

    No Known Activations