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

    Neuronpedia

    INDEX
    Explanations

    coping

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     acid
    -0.07
    grp
    -0.07
     cái
    -0.07
     corps
    -0.07
    เข
    -0.07
     dado
    -0.07
     Tory
    -0.06
     Kings
    -0.06
    יג
    -0.06
     Gree
    -0.06
    POSITIVE LOGITS
     Concent
    0.09
    城乡居民
    0.07
     densities
    0.07
    现实中
    0.07
    ocities
    0.07
    濋
    0.07
    	Simple
    0.07
    (/^\
    0.07
     brutally
    0.07
    nowled
    0.07
    Act Density 0.029%

    No Known Activations