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

    Neuronpedia

    INDEX
    Explanations

    json, YAML - file types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .age
    -0.07
    ﮒ
    -0.07
    指纹
    -0.06
    ゛
    -0.06
    ändig
    -0.06
    孤立
    -0.06
    檄
    -0.06
    <Integer
    -0.06
    (username
    -0.06
     headers
    -0.06
    POSITIVE LOGITS
    estimated
    0.07
    )L
    0.07
    Interaction
    0.07
    EH
    0.07
    ?"↵↵
    0.07
     )↵↵
    0.07
     Fade
    0.07
    𝇚
    0.06
    oire
    0.06
     thú
    0.06
    Act Density 0.016%

    No Known Activations