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

    Neuronpedia

    INDEX
    Explanations

    other

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Forge
    -0.07
    ůst
    -0.07
    iggs
    -0.06
     Levy
    -0.06
     mean
    -0.06
     optics
    -0.06
    рог
    -0.06
    ш
    -0.06
    628
    -0.06
    ip
    -0.06
    POSITIVE LOGITS
    Behind
    0.07
    ổng
    0.06
    $query
    0.06
    -controls
    0.06
     муж
    0.06
    redirectTo
    0.06
     ­
    0.06
     {?>↵
    0.06
     Ї
    0.06
    "]=>
    0.06
    Act Density 0.096%

    No Known Activations