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

    Neuronpedia

    INDEX
    Explanations

    chemical/scientific names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    åIJĦæł·
    -0.29
     siden
    -0.28
    plural
    -0.28
    羣å®ŀ
    -0.27
    ollen
    -0.26
     prox
    -0.26
     kort
    -0.26
    æĹģ
    -0.25
    ubic
    -0.25
    kowski
    -0.25
    POSITIVE LOGITS
    æľºåŀĭ
    0.30
     ç¼
    0.27
    建åĨĽ
    0.26
     Scale
    0.26
    [from
    0.25
    atcher
    0.25
     Ñĩа
    0.25
    åĪĹ
    0.25
    zelf
    0.24
     hunted
    0.24
    Act Density 0.035%

    No Known Activations