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

    Neuronpedia

    INDEX
    Explanations

    patterns related to numerical data and calculations

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

    Commas, semicolons, and math symbols

    np_acts-logits-general · gemini-2.0-flash

    math numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Alive
    -0.56
     <<<<<<<<<<<<<<
    -0.54
    alive
    -0.51
     LIV
    -0.49
     alive
    -0.49
     ALIVE
    -0.46
    érations
    -0.46
    生存
    -0.46
    LIV
    -0.45
     sobrevivir
    -0.45
    POSITIVE LOGITS
     autorytatywna
    0.87
    ThroughAttribute
    0.76
     <=",
    0.72
    SerializedSize
    0.71
    ंदीखरीदारी
    0.68
    ContentAsync
    0.67
    ///</
    0.65
    writeFieldEnd
    0.64
    ِّف
    0.64
     nahilalakip
    0.64
    Act Density 0.537%

    No Known Activations