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

    Neuronpedia

    INDEX
    Explanations

    email deliverability issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ！↵↵
    -0.06
     runner
    -0.06
    -inch
    -0.06
    >y
    -0.06
    日期
    -0.05
    ‐
    -0.05
     ami
    -0.05
    iale
    -0.05
    скільки
    -0.05
     unusual
    -0.05
    POSITIVE LOGITS
    �
    0.07
    .sigmoid
    0.07
    etal
    0.07
    Υ
    0.07
     posture
    0.07
    .tsv
    0.07
     Buckley
    0.07
    UMMY
    0.07
     offense
    0.06
    Disposition
    0.06
    Act Density 0.101%

    No Known Activations