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

    Neuronpedia

    INDEX
    Explanations

    anything

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jointly
    -0.06
     нік
    -0.06
    	items
    -0.06
     ctl
    -0.06
     _('
    -0.06
     英
    -0.06
     baja
    -0.06
    ाऊ
    -0.06
    ita
    -0.06
    .Ui
    -0.06
    POSITIVE LOGITS
     تحصیل
    0.07
    Britain
    0.06
    ancellationToken
    0.06
     sağlamak
    0.06
    _DGRAM
    0.06
     Accessed
    0.06
    manship
    0.06
     관한
    0.06
     Bài
    0.06
    альном
    0.06
    Act Density 0.004%

    No Known Activations