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

    Neuronpedia

    INDEX
    Explanations

    completion or officiality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SS
    -0.08
    同步
    -0.07
     jumping
    -0.07
    热带
    -0.07
    傲
    -0.07
    内陆
    -0.07
     الفت
    -0.06
    .parseFloat
    -0.06
    ᵨ
    -0.06
    ♜
    -0.06
    POSITIVE LOGITS
     emerges
    0.07
    ialias
    0.07
    stroy
    0.07
    ürn
    0.07
     cocos
    0.06
    مكان
    0.06
     ending
    0.06
     millones
    0.06
    ериал
    0.06
    (mail
    0.06
    Act Density 0.003%

    No Known Activations