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

    Neuronpedia

    INDEX
    Explanations

    band breakups

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -third
    -0.07
    (boolean
    -0.06
     Shah
    -0.06
    างว
    -0.06
     CNBC
    -0.06
     nguồn
    -0.06
    نس
    -0.06
     continuing
    -0.06
     RADIO
    -0.06
     улы
    -0.06
    POSITIVE LOGITS
     superintendent
    0.07
    ابق
    0.07
    ?>↵↵↵
    0.07
     philosopher
    0.07
    �数
    0.06
     /↵↵
    0.06
    otherwise
    0.06
    ρε
    0.06
    _STATS
    0.06
     математи
    0.06
    Act Density 0.029%

    No Known Activations