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

    Neuronpedia

    INDEX
    Explanations

    say the ending "-ong"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Trey
    -0.06
     RadioButton
    -0.06
    恐
    -0.06
    	strcat
    -0.06
    商
    -0.06
     فرانسه
    -0.06
     --
    -0.06
     ведь
    -0.06
     المغرب
    -0.06
    StringLength
    -0.06
    POSITIVE LOGITS
    holes
    0.07
    alaxy
    0.07
    mmc
    0.07
    passwd
    0.07
    _matrix
    0.07
    maximum
    0.07
    _ASYNC
    0.07
    umm
    0.07
    poi
    0.06
    flows
    0.06
    Act Density 0.001%

    No Known Activations