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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ıyı
    -0.07
    _FIRE
    -0.07
    _measurement
    -0.06
     плен
    -0.06
    poser
    -0.06
     bbox
    -0.06
    �
    -0.06
    =""><
    -0.06
    沢
    -0.06
    zen
    -0.06
    POSITIVE LOGITS
    urm
    0.07
     url
    0.06
     advise
    0.06
     fikir
    0.06
     overshadow
    0.06
    ippi
    0.06
     Civic
    0.06
     negative
    0.06
    (fullfile
    0.06
    =url
    0.06
    Act Density 0.021%

    No Known Activations