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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atisch
    -0.07
     overlaps
    -0.07
    مه
    -0.07
    lh
    -0.07
    اته
    -0.07
     מהווה
    -0.07
     אליה
    -0.07
    >Please
    -0.07
    ITIONS
    -0.06
    LING
    -0.06
    POSITIVE LOGITS
    컁
    0.08
    赞誉
    0.07
    שיווק
    0.07
    because
    0.07
    脆
    0.07
     $($
    0.07
    .Sub
    0.07
    腙
    0.07
     Risk
    0.07
     Clover
    0.07
    Act Density 0.041%

    No Known Activations