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
    _edge
    -0.07
    	usage
    -0.07
     příspě
    -0.06
     �
    -0.06
     overwhelmingly
    -0.06
     itemBuilder
    -0.06
     integers
    -0.06
     breakout
    -0.06
     elseif
    -0.06
     même
    -0.06
    POSITIVE LOGITS
     fet
    0.07
     scare
    0.06
     hely
    0.06
     Respect
    0.06
    成功
    0.06
     Fetish
    0.06
    aber
    0.06
    inesis
    0.06
    /";↵
    0.06
     chia
    0.06
    Act Density 0.060%

    No Known Activations