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

    Neuronpedia

    INDEX
    Explanations

    imposter syndrome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     core
    0.75
     Core
    0.66
    Core
    0.66
    核心
    0.65
    core
    0.64
     CORE
    0.63
    コア
    0.57
    CORE
    0.54
    的核心
    0.53
     cores
    0.46
    POSITIVE LOGITS
     impost
    1.28
     imperson
    1.08
     imp
    0.75
     Imp
    0.73
     fraud
    0.63
    poster
    0.62
     impersonal
    0.62
    fraud
    0.62
     usur
    0.59
    Fraud
    0.58
    Act Density 0.008%

    No Known Activations