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

    Neuronpedia

    INDEX
    Explanations

    deployment job

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     while
    1.20
    urra
    1.09
    While
    1.07
    atal
    0.99
    ynd
    0.95
     could
    0.94
    while
    0.94
    Diary
    0.93
    gegevens
    0.93
     whilst
    0.90
    POSITIVE LOGITS
     varying
    2.43
     caliber
    2.43
    varying
    2.26
     высоким
    2.25
    较高
    2.20
     undetermined
    2.20
    質な
    2.18
     najwy
    2.16
    グレード
    2.16
     stature
    2.14
    Act Density 0.139%

    No Known Activations