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

    Neuronpedia

    INDEX
    Explanations

    reject

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plays
    -0.07
     Drum
    -0.06
    fstream
    -0.06
     hablar
    -0.06
    are
    -0.06
    EndDate
    -0.06
    歷
    -0.06
    寫
    -0.06
    _STRUCTURE
    -0.06
     juris
    -0.06
    POSITIVE LOGITS
     rejected
    0.07
     Reject
    0.07
    ioned
    0.07
    ılmaktadır
    0.06
    repeat
    0.06
     reject
    0.06
     tough
    0.06
     contradiction
    0.06
    sock
    0.06
    icts
    0.06
    Act Density 0.008%

    No Known Activations