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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols used in formatting text

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

    Text inside parentheses

    np_acts-logits-general · gemini-2.0-flash

    closing parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     feroit
    -0.48
     Técnico
    -0.45
     the
    -0.42
     avoient
    -0.41
     auroit
    -0.40
     šk
    -0.39
     aislado
    -0.38
    Erreferentziak
    -0.36
     isolation
    -0.35
     geométrico
    -0.35
    POSITIVE LOGITS
    Personendaten
    0.77
    saraba
    0.76
     betweenstory
    0.67
    webElementXpaths
    0.65
    °)
    0.63
    цездатний
    0.62
    mybatisplus
    0.61
     (%)
    0.60
    ).)
    0.60
     Chwiliwch
    0.60
    Act Density 0.873%

    No Known Activations