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

    Neuronpedia

    INDEX
    Explanations

    {|

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .IsEnabled
    -0.08
    著作权
    -0.07
     שצריך
    -0.07
    鳒
    -0.07
    》，
    -0.07
    asonic
    -0.07
    ADED
    -0.06
     Riding
    -0.06
    _remaining
    -0.06
    3
    -0.06
    POSITIVE LOGITS
     
↵
↵
    0.07
    <F
    0.07
    "`↵
    0.07
    =''↵
    0.07
    겈
    0.06
    ----↵↵
    0.06
     fantasy
    0.06
    Cur
    0.06
    ～↵↵
    0.06
    -----↵↵
    0.06
    Act Density 0.001%

    No Known Activations