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

    Neuronpedia

    INDEX
    Explanations

    various forms of punctuation, specifically periods

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

    people and character descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wikipagina
    -0.43
     mismas
    -0.36
     Bewußt
    -0.36
    queles
    -0.35
     terkena
    -0.35
    agissait
    -0.35
    -0.35
     caramelo
    -0.35
     dipende
    -0.34
    RTLI
    -0.34
    POSITIVE LOGITS
     pleaſure
    0.55
     ſever
    0.53
     متعلقه
    0.49
    ftant
    0.48
    .*")]
    0.47
    úgó
    0.47
    msgTypes
    0.47
     CanadaChoose
    0.47
     purpoſe
    0.46
    protoimpl
    0.46
    Act Density 0.001%

    No Known Activations