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

    Neuronpedia

    INDEX
    Explanations

    Ordinal numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (strcmp
    -0.07
    元宝
    -0.07
    _COMBO
    -0.07
     advis
    -0.07
    -scal
    -0.07
    /mit
    -0.07
    resent
    -0.06
     Vis
    -0.06
     мод
    -0.06
    xdb
    -0.06
    POSITIVE LOGITS
    탉
    0.07
     former
    0.06
     المختلف
    0.06
    	template
    0.06
     identity
    0.06
     đã
    0.06
    ッグ
    0.06
    articles
    0.06
    awah
    0.06
    ían
    0.06
    Act Density 0.016%

    No Known Activations