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

    Neuronpedia

    INDEX
    Explanations

    common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .cons
    -0.06
     Ass
    -0.06
     =================================================================
    -0.06
     Astronomy
    -0.06
    FSIZE
    -0.06
     UNIVERS
    -0.06
    _ds
    -0.06
    .repaint
    -0.06
     Freddie
    -0.06
    	spec
    -0.06
    POSITIVE LOGITS
    obra
    0.07
     halk
    0.06
     DateTimeOffset
    0.06
     packages
    0.06
     nanop
    0.06
     sensitivity
    0.06
    โครงการ
    0.06
     confused
    0.06
    取得
    0.06
    platz
    0.06
    Act Density 0.090%

    No Known Activations