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

    Neuronpedia

    INDEX
    Explanations

    filtering

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prefab
    -0.07
     COMPLETE
    -0.07
    つい
    -0.07
    isten
    -0.07
    ピー
    -0.07
    浜
    -0.07
    _SPEED
    -0.07
    锛
    -0.07
    パン
    -0.07
    (Console
    -0.07
    POSITIVE LOGITS
    noc
    0.07
    我没有
    0.07
     fleeting
    0.07
     ipt
    0.07
    :]:↵
    0.07
     challenges
    0.07
    롓
    0.06
     jun
    0.06
     setback
    0.06
     mitigation
    0.06
    Act Density 0.001%

    No Known Activations