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

    Neuronpedia

    INDEX
    Explanations

    rules and policies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Armen
    -0.07
    ені
    -0.06
     pornografia
    -0.06
    -chevron
    -0.06
     مؤ
    -0.06
    ��
    -0.06
    ):\
    -0.05
    능
    -0.05
     �
    -0.05
    ocê
    -0.05
    POSITIVE LOGITS
     FileSystem
    0.07
     hanno
    0.06
     náklady
    0.06
    .removeListener
    0.06
     zih
    0.06
     FormData
    0.06
     nejd
    0.06
     admins
    0.06
     zusammen
    0.06
     initialise
    0.06
    Act Density 0.003%

    No Known Activations