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

    Neuronpedia

    INDEX
    Explanations

    terms related to compatibility and backward compatibility in software or code

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

    compatibility and legacy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    はじめに
    -0.47
    中野
    -0.34
    iertamente
    -0.32
     gre
    -0.30
     abstrait
    -0.30
     rend
    -0.30
     spurt
    -0.30
    市镇
    -0.29
     Watch
    -0.29
     generales
    -0.29
    POSITIVE LOGITS
     compati
    0.63
    prefixer
    0.60
     older
    0.60
     outdated
    0.59
     älteren
    0.58
     vecchi
    0.58
    legacy
    0.57
    upgrade
    0.57
    compati
    0.57
    Upgrade
    0.57
    Act Density 0.301%

    No Known Activations