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

    Neuronpedia

    INDEX
    Explanations

    ical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    休
    -0.07
    _fh
    -0.07
    司
    -0.07
    IENCE
    -0.06
     mús
    -0.06
    _song
    -0.06
    .But
    -0.06
    .sparse
    -0.06
     تور
    -0.06
    .USER
    -0.06
    POSITIVE LOGITS
     radical
    0.16
     Radical
    0.15
     radicals
    0.12
     radically
    0.10
     Rad
    0.09
    Rad
    0.09
     rad
    0.07
     acts
    0.07
    351
    0.07
     RC
    0.07
    Act Density 0.003%

    No Known Activations