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

    Neuronpedia

    INDEX
    Explanations

    scale

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     live
    -0.07
     autofocus
    -0.07
    σ
    -0.06
     термін
    -0.06
    іль
    -0.06
     tầng
    -0.06
    iciar
    -0.06
     lộ
    -0.06
    uforia
    -0.06
     village
    -0.06
    POSITIVE LOGITS
     kak
    0.07
    Implemented
    0.07
    (datas
    0.07
     scaled
    0.06
    PLAN
    0.06
     oppos
    0.06
    PPP
    0.06
    atal
    0.06
     */↵↵↵
    0.06
    });↵
    0.06
    Act Density 0.013%

    No Known Activations