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

    Neuronpedia

    INDEX
    Explanations

    highlight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    搔
    -0.07
    ≥
    -0.07
     Sage
    -0.07
     secs
    -0.07
    cales
    -0.07
     CSC
    -0.07
     rob
    -0.07
    Reset
    -0.07
    elsius
    -0.07
    ┐
    -0.07
    POSITIVE LOGITS
    目の
    0.08
    เราก
    0.07
    中间
    0.07
    yat
    0.07
     getClient
    0.07
     usernames
    0.07
    غل
    0.07
    פתח
    0.07
    ightly
    0.07
    LAT
    0.07
    Act Density 0.016%

    No Known Activations