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

    Neuronpedia

    INDEX
    Explanations

    diseases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    prop
    -0.07
    Fast
    -0.07
    averse
    -0.07
    ゥ
    -0.06
    Vis
    -0.06
    𝗢
    -0.06
    开朗
    -0.06
    PROFILE
    -0.06
    杈
    -0.06
    .semantic
    -0.06
    POSITIVE LOGITS
    校外
    0.07
    .Filters
    0.07
    Authenticate
    0.07
     taskId
    0.07
     משמעותי
    0.07
    可惜
    0.07
     implementations
    0.07
     случ
    0.07
     rigs
    0.06
     genitals
    0.06
    Act Density 0.000%

    No Known Activations