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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms indicating hierarchical levels or rankings

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

    level or niveau

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    erapeutics
    -0.40
    xFC
    -0.40
    agoza
    -0.40
     braccia
    -0.40
     Australie
    -0.39
    ใหญ่
    -0.39
     Kunst
    -0.39
     Inoc
    -0.38
    дыду
    -0.38
    hoeddwyd
    -0.37
    POSITIVE LOGITS
     level
    1.75
     levels
    1.59
    Level
    1.58
     Level
    1.55
     LEVEL
    1.53
    Levels
    1.52
    level
    1.52
     niveau
    1.52
     Levels
    1.49
    LEVEL
    1.48
    Act Density 0.051%

    No Known Activations