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

    Neuronpedia

    INDEX
    Explanations

    character

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    干旱
    -0.08
    .");
    -0.07
     Brooke
    -0.07
    لد
    -0.07
    𝙀
    -0.07
     rm
    -0.07
     ()
    -0.07
     caucus
    -0.07
     Remote
    -0.07
    .RESET
    -0.06
    POSITIVE LOGITS
     poil
    0.07
    开盘
    0.07
    duplicate
    0.07
    transport
    0.07
    瞻
    0.07
    弹
    0.06
    HasBeen
    0.06
    ц
    0.06
     surfaced
    0.06
    uns
    0.06
    Act Density 0.026%

    No Known Activations