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

    Neuronpedia

    INDEX
    Explanations

    names of scholars and authors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TikTok
    0.44
     onboarding
    0.42
     impactful
    0.41
     alte
    0.40
     fleeting
    0.40
     thinly
    0.40
     sourcing
    0.39
     Instagram
    0.39
     KPIs
    0.38
     dito
    0.38
    POSITIVE LOGITS
     Exptl
    0.54
     Balliye
    0.52
    attiyam
    0.51
    䣰
    0.47
    óticos
    0.46
    侾
    0.46
     եւ
    0.46
    醝
    0.46
    盽
    0.45
    leqq
    0.45
    Act Density 0.041%

    No Known Activations