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

    Neuronpedia

    INDEX
    Explanations

    code and language structure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ้แก
    -0.07
    ือ
    -0.06
    Avatar
    -0.06
    éd
    -0.06
     Senator
    -0.06
    .remaining
    -0.06
    าว
    -0.06
    Absolute
    -0.06
     Forgot
    -0.06
    ð
    -0.06
    POSITIVE LOGITS
    acking
    0.07
    [data
    0.06
    <|start_header_id|>
    0.06
    Dating
    0.06
    leshooting
    0.06
    <message
    0.06
    STYLE
    0.06
    .esp
    0.06
    levision
    0.06
     пы
    0.06
    Act Density 0.000%

    No Known Activations