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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xFA
    -0.07
    	continue
    -0.06
    aya
    -0.06
    precated
    -0.06
    bish
    -0.06
    visa
    -0.06
    แป
    -0.06
    ιας
    -0.06
     ký
    -0.06
    STRU
    -0.06
    POSITIVE LOGITS
     alternative
    0.07
     Lieutenant
    0.07
     governing
    0.07
    (concat
    0.06
     δημιουργ
    0.06
    投資
    0.06
    keywords
    0.06
    (cr
    0.06
    建议
    0.06
     Creates
    0.06
    Act Density 0.002%

    No Known Activations