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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their variations

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

    closing code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    -0.45
     niemi
    -0.45
     and
    -0.44
    zów
    -0.43
    的样子
    -0.42
     Erben
    -0.41
    ,
    -0.41
    ↵↵
    -0.40
    ages
    -0.40
     And
    -0.40
    POSITIVE LOGITS
    enderror
    0.77
     MessageBoxIcon
    0.71
    GraphicsUnit
    0.69
    ThroughAttribute
    0.64
    MethodManager
    0.63
     GenerationType
    0.62
     defaultstate
    0.61
    RegistryLite
    0.59
    XmlAccessType
    0.57
    IndentedString
    0.57
    Act Density 0.188%

    No Known Activations