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

    Neuronpedia

    INDEX
    Explanations

    min

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Geschichte
    -0.07
    tas
    -0.06
     phần
    -0.06
    RA
    -0.06
    กว
    -0.06
     JavaScript
    -0.06
    ew
    -0.06
    tan
    -0.06
    yl
    -0.06
     Ну
    -0.06
    POSITIVE LOGITS
    폴
    0.07
    ICA
    0.07
     (;;)
    0.07
    Pad
    0.07
    ологичес
    0.07
     incarnation
    0.07
     '/',↵
    0.07
    weigh
    0.07
     tỷ
    0.06
     короб
    0.06
    Act Density 0.000%

    No Known Activations