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

    Neuronpedia

    INDEX
    Explanations

    terms related to operational advantages and indicators in various contexts

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

    evidence suggests or explanation for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     становника
    -0.47
    HomeAsUpEnabled
    -0.46
     flèche
    -0.41
     catto
    -0.40
     Falcons
    -0.38
    adins
    -0.36
     Autorisations
    -0.35
    adakan
    -0.35
    unteer
    -0.35
     Oilers
    -0.35
    POSITIVE LOGITS
    verwijspagina
    0.54
     disambiguazione
    0.49
     chì
    0.47
     ProductService
    0.43
     houſe
    0.42
    ſhip
    0.42
    UnusedPrivate
    0.41
    GEBURTS
    0.40
    المكان
    0.39
    isseaux
    0.39
    Act Density 0.475%

    No Known Activations