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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "like" in various contexts, often followed by expressions or comparisons

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

    code examples and math formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Rüyada
    -0.50
    oa̍t
    -0.47
    ilaian
    -0.41
    safe
    -0.39
     terecht
    -0.38
    Safe
    -0.37
     safe
    -0.36
    ंदीखरीदारी
    -0.35
     actualidad
    -0.34
    lief
    -0.34
    POSITIVE LOGITS
    IsMutable
    0.56
    parsedMessage
    0.54
    setVerticalGroup
    0.51
    DockStyle
    0.51
    HasAnnotation
    0.50
    CloseOperation
    0.49
    protoimpl
    0.46
     disambiguazione
    0.45
     sumpay
    0.44
    contentLoaded
    0.44
    Act Density 0.390%

    No Known Activations