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

    Neuronpedia

    INDEX
    Explanations

    code or configuration files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     withstand
    -0.09
    Fight
    -0.08
     Fight
    -0.07
     Ki
    -0.07
    LI
    -0.07
    igate
    -0.06
    he
    -0.06
    Road
    -0.06
     trap
    -0.06
     Reynolds
    -0.06
    POSITIVE LOGITS
     spíše
    0.07
    mayacak
    0.07
     donde
    0.06
     دنیا
    0.06
     espect
    0.06
     [['
    0.06
    EXTERN
    0.06
     OMX
    0.06
     OUR
    0.06
    也是
    0.06
    Act Density 0.011%

    No Known Activations