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

    Neuronpedia

    INDEX
    Explanations

    researchers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Button
    -0.08
    راف
    -0.07
     Niger
    -0.07
     Depends
    -0.07
     train
    -0.06
    ije
    -0.06
    Cd
    -0.06
    jezd
    -0.06
    易
    -0.06
     Element
    -0.06
    POSITIVE LOGITS
     etkin
    0.06
     scientist
    0.06
    .onPause
    0.06
    :NS
    0.06
     contestant
    0.06
    /,↵
    0.06
     quarterly
    0.06
    _ALWAYS
    0.06
    ưới
    0.06
    FSIZE
    0.06
    Act Density 0.004%

    No Known Activations