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

    Neuronpedia

    INDEX
    Explanations

    list item continuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     acost
    0.40
     =
    0.39
    蟻
    0.37
    逵
    0.37
     он
    0.36
    立刻
    0.36
     imper
    0.36
     Het
    0.36
    rals
    0.36
     기반
    0.36
    POSITIVE LOGITS
     pizzeria
    0.43
     mitad
    0.43
     februari
    0.42
     Elektrokhimiya
    0.42
    chromiumfx
    0.41
     falando
    0.40
    nahi
    0.39
     экономики
    0.39
     lingkaran
    0.38
    काळी
    0.38
    Act Density 0.001%

    No Known Activations