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

    Neuronpedia

    INDEX
    Explanations

    base

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    一项
    -0.07
     elevator
    -0.07
     infused
    -0.07
    اغ
    -0.07
    CT
    -0.07
     mutate
    -0.07
    (async
    -0.07
     oder
    -0.07
    𝐂
    -0.07
     coordination
    -0.07
    POSITIVE LOGITS
     Company
    0.07
    Forum
    0.07
    0.07
     ?>>↵
    0.07
    �
    0.06
     showroom
    0.06
     Ivanka
    0.06
    ategorias
    0.06
    ">(
    0.06
     BUT
    0.06
    Act Density 0.001%

    No Known Activations