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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Schmidt
    -0.07
     Chanel
    -0.07
    φό
    -0.07
    (PR
    -0.06
     McM
    -0.06
    ouv
    -0.06
    onde
    -0.06
    ace
    -0.06
     Curry
    -0.06
    ula
    -0.06
    POSITIVE LOGITS
    厅
    0.06
     crem
    0.06
    퓨터
    0.06
    )->
    0.06
    Cent
    0.06
    něm
    0.06
    _BIG
    0.06
    _ub
    0.06
    ті
    0.05
    ign
    0.05
    Act Density 0.077%

    No Known Activations