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

    Neuronpedia

    INDEX
    Explanations

    atomic bomb and kernel driver

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    整
    0.44
    igh
    0.42
    DH
    0.41
    gart
    0.41
    ft
    0.40
     Frage
    0.40
    ih
    0.40
    юр
    0.39
    स्फोट
    0.38
    planning
    0.38
    POSITIVE LOGITS
    ólito
    0.38
    +|
    0.38
     tilting
    0.38
     Lorena
    0.37
     Astronomy
    0.36
    ANTES
    0.36
    ющегося
    0.35
    ेंसी
    0.35
    Til
    0.35
    abies
    0.35
    Act Density 0.000%

    No Known Activations