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

    Neuronpedia

    INDEX
    Explanations

    may

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    doing
    -0.07
    (pow
    -0.07
     تسم
    -0.07
     uninstall
    -0.07
    .PO
    -0.07
     указ
    -0.07
    Skip
    -0.07
    _by
    -0.06
     склада
    -0.06
     exhibit
    -0.06
    POSITIVE LOGITS
     may
    0.09
     might
    0.08
    123
    0.07
    独
    0.06
    ライト
    0.06
     thé
    0.06
     Palm
    0.06
     intolerance
    0.06
    545
    0.05
    .att
    0.05
    Act Density 0.019%

    No Known Activations