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

    Neuronpedia

    INDEX
    Explanations

    code extracts/reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     insurer
    -0.08
    angles
    -0.07
    relay
    -0.07
     Scenes
    -0.07
    flare
    -0.07
    idend
    -0.07
    (flags
    -0.06
    door
    -0.06
    zoek
    -0.06
     anime
    -0.06
    POSITIVE LOGITS
    _HW
    0.06
    期
    0.06
    .mob
    0.06
    arious
    0.06
    >'+↵
    0.06
    60
    0.06
    _req
    0.06
    )]↵
    0.06
     airborne
    0.06
    "];↵
    0.06
    Act Density 0.158%

    No Known Activations