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

    Neuronpedia

    INDEX
    Explanations

    "inputs="

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝒹
    0.55
    FAILED
    0.50
    SHARED
    0.46
    ዋ
    0.46
     ailments
    0.46
     ज़्यादा
    0.46
    WILL
    0.46
    ドウ
    0.45
     Essays
    0.45
    乘以
    0.44
    POSITIVE LOGITS
    愤
    0.54
    isjon
    0.52
    ing
    0.50
    ].[
    0.48
    audioType
    0.48
     Geol
    0.47
    \
    0.47
    Ᏹ
    0.47
     flott
    0.46
    õ
    0.46
    Act Density 0.002%

    No Known Activations