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

    Neuronpedia

    INDEX
    Explanations

    Gratitude

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    圖
    -0.06
    zo
    -0.06
    Instances
    -0.06
     fried
    -0.06
     Sweep
    -0.06
    보았다
    -0.06
     Matcher
    -0.06
    loyment
    -0.06
     rue
    -0.06
    非
    -0.06
    POSITIVE LOGITS
    .cwd
    0.07
    ISION
    0.07
     BaseActivity
    0.07
     SES
    0.07
    Generally
    0.07
    Traditional
    0.07
     ＜
    0.07
    _POOL
    0.06
    _NAMESPACE
    0.06
    .Time
    0.06
    Act Density 0.024%

    No Known Activations