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

    Neuronpedia

    INDEX
    Explanations

    Research studies, publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Disc
    -0.28
     fulfil
    -0.28
    /disc
    -0.27
    ì§ij
    -0.27
    ãģĤãģŁãĤĬ
    -0.27
    ervals
    -0.26
    ä¸įæľį
    -0.25
    EventData
    -0.25
    纪å¾ĭ
    -0.25
    auses
    -0.24
    POSITIVE LOGITS
    ä¸ĭ乡
    0.28
    po
    0.28
     probe
    0.26
    .shtml
    0.26
    .biz
    0.25
    æİ¢
    0.25
     Biz
    0.25
     probes
    0.25
    å¤ļå¤ļ
    0.25
     linked
    0.24
    Act Density 0.012%

    No Known Activations