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

    Neuronpedia

    INDEX
    Explanations

    punctuation/stopwords

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ινη
    -0.07
    iphone
    -0.07
     Maintain
    -0.07
    Caption
    -0.06
    меч
    -0.06
    extView
    -0.06
     crusher
    -0.06
    lix
    -0.06
    (seg
    -0.06
    енс
    -0.06
    POSITIVE LOGITS
    _|
    0.06
    .HttpServletRequest
    0.06
     afflicted
    0.06
    '>"
    0.06
    ]])
    0.06
    _ACCEPT
    0.06
    連
    0.06
    开放
    0.06
     XV
    0.06
    #pragma
    0.06
    Act Density 0.385%

    No Known Activations