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

    Neuronpedia

    INDEX
    Explanations

    patterns and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enlist
    1.23
     surpluses
    1.20
     shoulders
    1.18
     protrusions
    1.17
     fists
    1.09
     uncertainties
    1.08
    ality
    1.08
    inescence
    1.07
     fluxes
    1.07
    ২৭
    1.07
    POSITIVE LOGITS
    า
    1.40
    𝐔
    1.30
    е
    1.17
    झे
    1.12
    𝐮
    1.10
    𝐧
    1.06
    ُوا
    1.04
    λασ
    1.04
     orden
    1.03
    ాప
    1.02
    Act Density 0.000%

    No Known Activations