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

    Neuronpedia

    INDEX
    Explanations

    emails

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    頂
    -0.08
     ER
    -0.07
    itionally
    -0.07
     trunk
    -0.07
     fur
    -0.06
    *v
    -0.06
     advanced
    -0.06
     stil
    -0.06
    -sign
    -0.06
     द
    -0.06
    POSITIVE LOGITS
    fragistics
    0.08
     Infragistics
    0.07
     �
    0.07
    Sans
    0.07
     ToString
    0.06
    stashop
    0.06
    lok
    0.06
     neut
    0.06
    تي
    0.06
    	atomic
    0.06
    Act Density 0.033%

    No Known Activations