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

    Neuronpedia

    INDEX
    Explanations

    structural elements of code or programming syntax

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

    end of test block

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.70
    PropertyChanging
    -0.68
     Infór
    -0.65
    ſcher
    -0.64
    tableFuture
    -0.63
     MainAxisSize
    -0.62
     وتسجيلات
    -0.62
     iprot
    -0.61
    iſen
    -0.61
     autorytatywna
    -0.61
    POSITIVE LOGITS
    <eos>
    0.42
    <h2>
    0.41
     accurate
    0.37
     even
    0.34
     Do
    0.33
    院
    0.32
     accuracy
    0.32
     if
    0.32
     odd
    0.32
     Beware
    0.32
    Act Density 0.006%

    No Known Activations