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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     courteous
    -0.07
     presumption
    -0.06
     slur
    -0.06
    isan
    -0.06
     siguiente
    -0.06
    Sean
    -0.06
     شی
    -0.06
    ebilecek
    -0.06
     condemnation
    -0.06
     prisoner
    -0.06
    POSITIVE LOGITS
    .HtmlControls
    0.06
    (struct
    0.06
     million
    0.06
    .JFrame
    0.06
    زة
    0.06
     Counseling
    0.06
     Ц
    0.06
     Mathematic
    0.06
     authorised
    0.06
    wrapped
    0.06
    Act Density 0.047%

    No Known Activations