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

    Neuronpedia

    INDEX
    Explanations

    sequence generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    e
    0.43
     liquides
    0.42
    ní
    0.41
    ú
    0.40
    ered
    0.40
    짙
    0.39
    tax
    0.39
    с
    0.39
     wund
    0.38
    ismi
    0.38
    POSITIVE LOGITS
     Acting
    0.50
     Qin
    0.44
    !!!!!!
    0.44
    📕
    0.44
    𝓖
    0.44
     modulating
    0.42
     PHONE
    0.42
    AGING
    0.42
    QUARE
    0.42
    🚃
    0.41
    Act Density 0.002%

    No Known Activations