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

    Neuronpedia

    INDEX
    Explanations

    depends on or however

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    restrial
    0.43
    تس
    0.42
    sic
    0.40
    kans
    0.40
    Authors
    0.40
    ToString
    0.39
    Multicolored
    0.39
    <0xAF>
    0.39
    es
    0.39
    :',
    0.39
    POSITIVE LOGITS
     özellikleri
    0.49
     actuellement
    0.48
    ಟನೆ
    0.47
     Peki
    0.47
     网
    0.46
    咶
    0.45
    ദ്ധി
    0.45
     gentlemen
    0.45
     crappy
    0.45
    ሉ።
    0.44
    Act Density 0.006%

    No Known Activations