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

    Neuronpedia

    INDEX
    Explanations

    comparisons across multiple datasets or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    comparing items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inoxydable
    -0.34
    šanās
    -0.30
     گرد
    -0.30
     páss
    -0.29
     vastaan
    -0.28
    addGap
    -0.28
     garaje
    -0.27
    tské
    -0.27
    pyx
    -0.25
     život
    -0.25
    POSITIVE LOGITS
    хьтан
    0.80
    Personendaten
    0.66
     Verſ
    0.66
    IVEREF
    0.65
     Geſch
    0.65
    0.63
    astify
    0.63
    期刊论文
    0.63
    новништво
    0.61
     Meksiku
    0.60
    Act Density 0.468%

    No Known Activations