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

    Neuronpedia

    INDEX
    Explanations

    methods and ways

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     distinto
    0.48
    etze
    0.46
    iesen
    0.45
    vas
    0.44
    bac
    0.44
    irii
    0.44
    τ
    0.43
     تد
    0.43
     invigor
    0.42
    maw
    0.42
    POSITIVE LOGITS
     fluctuating
    0.45
    走了
    0.42
    PARAMETERS
    0.41
    一眼
    0.40
    המ
    0.40
    Instant
    0.40
    これは
    0.40
    हरूको
    0.40
    商店
    0.40
    根據
    0.39
    Act Density 0.002%

    No Known Activations