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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ASCII
    -0.08
    _ascii
    -0.07
     told
    -0.07
    录
    -0.07
    了承
    -0.07
    纪
    -0.07
     Twitch
    -0.07
    比赛
    -0.07
     Claude
    -0.07
     Abdullah
    -0.07
    POSITIVE LOGITS
    状態
    0.10
     अवस्थ
    0.10
    .Pending
    0.10
     unresolved
    0.10
    .pending
    0.10
     состоянии
    0.10
    _PENDING
    0.09
     patiently
    0.09
     상태
    0.09
    waiting
    0.09
    Act Density 0.100%

    No Known Activations