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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     igual
    -0.07
    eşit
    -0.07
     Nou
    -0.07
     Gio
    -0.07
    discord
    -0.07
     สล
    -0.06
     행동
    -0.06
    사지
    -0.06
    oenix
    -0.06
    isme
    -0.06
    POSITIVE LOGITS
     containers
    0.07
     mức
    0.06
    _Customer
    0.06
     Inserts
    0.06
     місці
    0.06
    -books
    0.06
     esc
    0.06
    НИ
    0.06
     нескольких
    0.06
     پزشکی
    0.06
    Act Density 0.004%

    No Known Activations