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

    Neuronpedia

    INDEX
    Explanations

    artifactId closing >

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     symplect
    0.45
    presso
    0.41
    newMark
    0.41
    ObjectUnderTest
    0.40
    esam
    0.40
    oulli
    0.39
    OpportunitiesBy
    0.39
    itioners
    0.38
     convexe
    0.38
    ={`
    0.38
    POSITIVE LOGITS
    G
    0.37
     ACC
    0.37
    備
    0.36
    备
    0.35
     kup
    0.34
    ACC
    0.33
     版
    0.33
     sl
    0.32
    H
    0.32
    acc
    0.32
    Act Density 0.001%

    No Known Activations