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

    Neuronpedia

    INDEX
    Explanations

    text generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     R
    0.68
    R
    0.58
     الر
    0.52
     ROUILLER
    0.46
    Р
    0.46
    𝑅
    0.46
    Ռ
    0.45
    𝚁
    0.44
     ร
    0.43
    Alex
    0.43
    POSITIVE LOGITS
    阑
    0.39
    闌
    0.38
     Hun
    0.35
     अध
    0.34
     Mann
    0.34
     Hugh
    0.34
    Hugh
    0.33
    XT
    0.32
     Dess
    0.32
     abort
    0.32
    Act Density 0.007%

    No Known Activations