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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CHEDULE
    -0.07
    appear
    -0.07
    agation
    -0.06
    pression
    -0.06
     adorn
    -0.06
     
    -0.06
    ому
    -0.06
    Ended
    -0.06
    /files
    -0.06
    머
    -0.06
    POSITIVE LOGITS
    	memset
    0.08
     slur
    0.07
     klient
    0.07
     akka
    0.07
    \Database
    0.07
     GUIStyle
    0.06
     invers
    0.06
     定
    0.06
     zih
    0.06
     ding
    0.06
    Act Density 0.003%

    No Known Activations