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

    Neuronpedia

    INDEX
    Explanations

    references to communication and expressions of feelings

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

    native english

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Italijani
    -0.66
     betweenstory
    -0.54
     Administrativna
    -0.53
     Савезне
    -0.52
    queryInterface
    -0.50
     الرياضيه
    -0.49
     Италијани
    -0.47
     Italijanski
    -0.46
     informée
    -0.45
    numerusform
    -0.41
    POSITIVE LOGITS
    SuspendLayout
    0.49
    verwijspagina
    0.44
     wheel
    0.44
    ExecuteReader
    0.42
    Feels
    0.42
     zipped
    0.42
    Grath
    0.42
    taki
    0.42
    ardia
    0.41
    wheel
    0.41
    Act Density 0.234%

    No Known Activations