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

    Neuronpedia

    INDEX
    Explanations

    instances of formatting or structured text in the document

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

    Text following uncommon punctuation or symbols

    np_acts-logits-general · gemini-2.0-flash

    Cocoa,GEBURTSDATUM, SerializedSize

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    стной
    -0.46
    Mish
    -0.42
     parha
    -0.42
     formaggio
    -0.42
    setState
    -0.41
     gela
    -0.41
    ToTensor
    -0.41
    ask
    -0.41
     trust
    -0.41
     Stra
    -0.40
    POSITIVE LOGITS
    
    1.14
    
    0.85
    GEBURTSDATUM
    0.83
    0.81
    SerializedSize
    0.80
    ंदीखरीदारी
    0.75
     OFDb
    0.75
     Cocoa
    0.75
    OGND
    0.75
     Мексичка
    0.74
    Act Density 0.069%

    No Known Activations