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

    Neuronpedia

    INDEX
    Explanations

    bbox

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Heidi
    -0.08
     hints
    -0.08
    \Post
    -0.07
     unset
    -0.07
    START
    -0.07
    �藏
    -0.07
     endorsed
    -0.07
     טי
    -0.07
    (sd
    -0.07
    -Dec
    -0.07
    POSITIVE LOGITS
    」「
    0.07
    鳠
    0.07
    ᕛ
    0.06
    翀
    0.06
    🐨
    0.06
    ꧈
    0.06
    △
    0.06
     которого
    0.06
    ____
    0.06
     gratuita
    0.06
    Act Density 0.003%

    No Known Activations