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

    Neuronpedia

    INDEX
    Explanations

    Math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     eta
    -0.07
     domicile
    -0.07
     lai
    -0.07
    ol
    -0.07
     &$
    -0.07
    	RT
    -0.07
    ,n
    -0.07
    争
    -0.06
    executor
    -0.06
    Str
    -0.06
    POSITIVE LOGITS
    ("\(
    0.06
    THIS
    0.06
    pcion
    0.06
    ادات
    0.06
     closets
    0.06
     ${(
    0.06
     breat
    0.06
    ermen
    0.06
     Throws
    0.06
    alement
    0.06
    Act Density 0.041%

    No Known Activations