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

    Neuronpedia

    INDEX
    Explanations

    maximum

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    善
    -0.09
     sensitive
    -0.08
    プライ
    -0.08
    elist
    -0.07
     skip
    -0.07
    ogenic
    -0.07
     propensity
    -0.07
    _req
    -0.07
    ضر
    -0.07
    交友
    -0.07
    POSITIVE LOGITS
    ☧
    0.07
    maximum
    0.07
    uyo
    0.07
     maximum
    0.07
    ║
    0.07
    얕
    0.07
     The
    0.07
     THE
    0.07
     the
    0.07
     Flam
    0.07
    Act Density 0.016%

    No Known Activations