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

    Neuronpedia

    INDEX
    Explanations

    y

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     perfected
    -0.08
    (update
    -0.07
     himself
    -0.07
    cook
    -0.07
     habitual
    -0.07
    .github
    -0.06
    Calls
    -0.06
    альних
    -0.06
    療
    -0.06
     feared
    -0.06
    POSITIVE LOGITS
     y
    0.07
    y
    0.07
    _jwt
    0.07
    ",
↵
    0.07
    ,y
    0.07
     ℝ
    0.07
     forControlEvents
    0.07
     Labs
    0.06
     Jeep
    0.06
    \DB
    0.06
    Act Density 0.020%

    No Known Activations