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

    Neuronpedia

    INDEX
    Explanations

    numbers and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     clientèle
    -1.10
    künfte
    -1.09
    كتشاف
    -1.05
    født
    -1.05
     }],
    -1.03
     melewati
    -1.03
     Uniti
    -1.02
    ジュアル
    -1.02
    Using
    -1.02
    któ
    -1.00
    POSITIVE LOGITS
     entire
    1.26
    â
    1.12
    à
    1.05
     elegantly
    1.00
     gesamte
    0.97
    no
    0.97
     intertw
    0.97
     ulicy
    0.97
    EDE
    0.95
    it
    0.95
    Act Density 0.110%

    No Known Activations