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

    Neuronpedia

    INDEX
    Explanations

    ai

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    扫
    -0.08
     descend
    -0.07
     todav
    -0.07
    沧
    -0.07
    巽
    -0.07
     вполн
    -0.07
    フル
    -0.07
    (StringUtils
    -0.07
     He
    -0.07
    龈
    -0.06
    POSITIVE LOGITS
    Chem
    0.07
    bugs
    0.06
    -loss
    0.06
     artworks
    0.06
    ？↵
    0.06
     ................
    0.06
    quets
    0.06
     glucose
    0.06
    .site
    0.06
    ellite
    0.06
    Act Density 0.003%

    No Known Activations