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

    Neuronpedia

    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chấp
    -0.06
    ίγ
    -0.06
    RC
    -0.06
     aktuální
    -0.06
    _first
    -0.06
    esi
    -0.06
    positions
    -0.06
     subscribing
    -0.06
     adapter
    -0.06
     програм
    -0.06
    POSITIVE LOGITS
    ağ
    0.07
     UNS
    0.06
     léč
    0.06
    /fl
    0.06
    taş
    0.06
    слов
    0.06
    Things
    0.06
    ,is
    0.06
     Kag
    0.06
    باد
    0.06
    Act Density 0.212%

    No Known Activations