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

    Neuronpedia

    INDEX
    Explanations

    estimation and estimator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    сным
    1.13
     Aussi
    1.12
    Ｅ
    1.03
    𝗔
    1.01
     tatsächlich
    0.98
    мышлен
    0.98
     Août
    0.96
     âmbito
    0.96
    𝗘
    0.96
    𝗞
    0.95
    POSITIVE LOGITS
    6
    0.91
     epinephrine
    0.91
    7
    0.87
    3
    0.87
    ه‌ی
    0.84
    9
    0.83
    5
    0.82
     nine
    0.80
    婆
    0.79
     bagel
    0.79
    Act Density 0.042%

    No Known Activations