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

    Neuronpedia

    INDEX
    Explanations

    United Way and unified concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    وغ
    0.43
    fr
    0.41
    Gü
    0.40
    p
    0.39
    B
    0.38
    php
    0.38
    મિંગ
    0.38
    pR
    0.37
    raseña
    0.37
    ლ
    0.37
    POSITIVE LOGITS
     unified
    0.92
    unified
    0.82
     united
    0.80
    Unified
    0.80
     Unified
    0.79
     unification
    0.77
    統一
    0.73
     unify
    0.73
    统一
    0.72
     unites
    0.69
    Act Density 0.008%

    No Known Activations