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

    Neuronpedia

    INDEX
    Explanations

    Chromium

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pname
    -0.07
    ,it
    -0.07
    这本书
    -0.07
    箦
    -0.07
     fils
    -0.06
    컽
    -0.06
    곾
    -0.06
    Outputs
    -0.06
    政协委员
    -0.06
    緣
    -0.06
    POSITIVE LOGITS
    _processor
    0.08
    -Smith
    0.07
     encryption
    0.07
    debug
    0.07
     Chargers
    0.07
     rituals
    0.07
    ("""↵
    0.07
    🚨
    0.07
     SPORT
    0.06
     specialists
    0.06
    Act Density 0.000%

    No Known Activations