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

    Neuronpedia

    INDEX
    Explanations

    Descriptive, technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     promote
    -0.07
    chedulers
    -0.07
    шили
    -0.07
     başında
    -0.07
    -checked
    -0.06
    дав
    -0.06
    ану
    -0.06
    动生成
    -0.06
    дан
    -0.06
    ेक
    -0.06
    POSITIVE LOGITS
     объяс
    0.07
    entric
    0.06
     USING
    0.06
    FTA
    0.06
    	read
    0.06
     coorden
    0.06
     Pace
    0.06
     cpp
    0.06
    pth
    0.06
     samostat
    0.06
    Act Density 0.086%

    No Known Activations