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

    Neuronpedia

    INDEX
    Explanations

    miscellaneous snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    کرد
    -0.07
     rhetorical
    -0.07
    لاة
    -0.07
    _adj
    -0.06
    áty
    -0.06
     tanın
    -0.06
     este
    -0.06
    bilir
    -0.06
     그녀는
    -0.06
     فرز
    -0.06
    POSITIVE LOGITS
    Observable
    0.07
     destination
    0.07
    (deg
    0.06
    ::$
    0.06
    _Act
    0.06
    .ravel
    0.06
    _OFFSET
    0.06
    _ON
    0.06
     Waterloo
    0.06
    /*----------------------------------------------------------------------------
    0.06
    Act Density 0.285%

    No Known Activations