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

    Neuronpedia

    INDEX
    Explanations

    positive evaluations and descriptions of food and dining experiences

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

    positive descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    avut
    -0.33
     רג
    -0.32
    おめでとうございます
    -0.32
     informée
    -0.32
     Vor
    -0.32
     Tour
    -0.32
     Touren
    -0.31
     numerus
    -0.31
     heaviest
    -0.31
     broader
    -0.31
    POSITIVE LOGITS
    Jîn
    0.62
     nakalista
    0.59
    ConstraintMaker
    0.57
    sizeCache
    0.55
    SharedDtor
    0.55
    VYMaps
    0.54
    ☚
    0.53
    dyž
    0.52
    ArgsConstructor
    0.49
    ftagPool
    0.49
    Act Density 0.023%

    No Known Activations