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
     praised
    -0.07
     deployed
    -0.07
    punkt
    -0.07
    绝
    -0.07
     rise
    -0.07
    punk
    -0.07
     ARR
    -0.07
     Door
    -0.07
     Nacht
    -0.06
    Story
    -0.06
    POSITIVE LOGITS
    ');↵↵↵
    0.07
    	Response
    0.06
     '\''
    0.06
    コン
    0.06
    _LVL
    0.06
     "?
    0.06
     '".$_
    0.06
    _SANITIZE
    0.06
     Володими
    0.06
    (optional
    0.06
    Act Density 0.067%

    No Known Activations