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

    Neuronpedia

    INDEX
    Explanations

    removal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ціка
    -0.07
    GBP
    -0.07
    idla
    -0.07
    _framework
    -0.06
    uously
    -0.06
    -designed
    -0.06
    しょ
    -0.06
    �
    -0.06
    upid
    -0.06
    빌
    -0.06
    POSITIVE LOGITS
    REPORT
    0.07
     Replay
    0.06
     Minimal
    0.06
     Subject
    0.06
    PU
    0.06
     commas
    0.06
    olver
    0.06
     suits
    0.06
    .for
    0.06
    染
    0.06
    Act Density 0.001%

    No Known Activations