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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating ease or simplicity in tasks

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

    ease of use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     виправивши
    -0.50
    Jeografia
    -0.48
    archiviato
    -0.44
     ligiloj
    -0.43
    LookAnd
    -0.41
     resourceCulture
    -0.41
    wnież
    -0.40
    MockMvc
    -0.39
    writeFieldEnd
    -0.37
     numberWith
    -0.36
    POSITIVE LOGITS
    quick
    0.61
     EASY
    0.60
    basic
    0.60
    EASY
    0.59
    easy
    0.59
    recipes
    0.59
    簡単
    0.58
     quickest
    0.58
     simplified
    0.57
    recipe
    0.56
    Act Density 0.009%

    No Known Activations