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

    Neuronpedia

    INDEX
    Explanations

    streaming operator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     표
    0.42
    dos
    0.38
    DVD
    0.37
    SAS
    0.36
    iant
    0.36
    Uttar
    0.36
    バイ
    0.36
    怎樣
    0.35
    osomes
    0.35
    裘
    0.34
    POSITIVE LOGITS
     condiv
    0.41
     insane
    0.41
     geschaffen
    0.40
     efect
    0.40
     mantenere
    0.40
     leta
    0.40
     possibilit
    0.40
     atr
    0.39
     reali
    0.38
     possibility
    0.38
    Act Density 0.000%

    No Known Activations