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

    Neuronpedia

    INDEX
    Explanations

    Searching online

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cinematic
    -0.07
     golden
    -0.07
     куд
    -0.07
    cı
    -0.07
    厚厚
    -0.07
    披露
    -0.07
     icy
    -0.06
    FUL
    -0.06
    챈
    -0.06
    无助
    -0.06
    POSITIVE LOGITS
    ↵↵↵↵↵↵↵
    0.07
    '})↵↵
    0.07
    Dialog
    0.07
     Louisville
    0.07
    lat
    0.06
    ->{_
    0.06
     enterprises
    0.06
     Mia
    0.06
     plaintext
    0.06
    �
    0.06
    Act Density 0.034%

    No Known Activations