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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    茵
    -0.07
     Mushroom
    -0.07
     Bay
    -0.07
    煳
    -0.07
    锆
    -0.06
     °
    -0.06
    国家重点
    -0.06
     béné
    -0.06
    汜
    -0.06
     chemin
    -0.06
    POSITIVE LOGITS
     opera
    0.08
     strings
    0.08
    ;
↵
↵
    0.07
    ()){↵
    0.07
    ())),↵
    0.07
     haircut
    0.07
    ()){
↵
    0.07
    ligt
    0.07
     sketch
    0.07
    ](↵
    0.07
    Act Density 0.005%

    No Known Activations