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

    Neuronpedia

    INDEX
    Explanations

    communication styles, mediums, or sites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    1.22
     \
    1.16
     (
    1.09
    0.99
    在
    0.94
    ión
    0.91
    cción
    0.87
    ’
    0.84
    कर
    0.83
    vention
    0.82
    POSITIVE LOGITS
    т
    1.30
     communication
    1.19
    ר
    1.10
    트
    1.09
    <0x80>
    1.08
    ی
    1.06
     communications
    1.05
    る
    1.05
     comunicación
    1.04
    ༨
    1.03
    Act Density 0.050%

    No Known Activations