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

    Neuronpedia

    INDEX
    Explanations

    Questions about the point

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    elled
    -0.08
    诣
    -0.08
     Tại
    -0.07
     Translate
    -0.07
     FontStyle
    -0.07
    LED
    -0.07
     ở
    -0.07
    滨海
    -0.07
    ilty
    -0.07
    oundation
    -0.07
    POSITIVE LOGITS
     NE
    0.07
     degrade
    0.07
    POSIT
    0.07
    分け
    0.07
    _converter
    0.07
    izard
    0.06
     observes
    0.06
     secre
    0.06
     LOCK
    0.06
    "\
    0.06
    Act Density 0.033%

    No Known Activations