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

    Neuronpedia

    INDEX
    Explanations

    dialogue and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     зокрема
    1.25
    鼠标
    1.15
     valamint
    1.12
     ofrecer
    1.12
    میں
    1.09
    如下图
    1.08
     autocorrelation
    1.07
     stakeholders
    1.05
    如果
    1.05
    这种
    1.05
    POSITIVE LOGITS
    $,
    0.85
    ᴛ
    0.83
    )!=
    0.83
    𝐬
    0.80
    ⌇
    0.79
    Neder
    0.78
    σης
    0.78
    ̵
    0.77
    𝕕
    0.77
     bø
    0.77
    Act Density 0.039%

    No Known Activations