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

    Neuronpedia

    INDEX
    Explanations

    instances of binary values or bit manipulation in code

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

    hex bitmasks and formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.72
     initComponents
    -0.57
    findpost
    -0.50
    ButterKnife
    -0.48
    contentLoaded
    -0.46
    -------------</
    -0.46
    ="@+
    -0.45
    parametrize
    -0.44
    ########.
    -0.44
    WebVitals
    -0.43
    POSITIVE LOGITS
     personnalisée
    0.52
    larında
    0.42
    ósitos
    0.42
     personnalisés
    0.40
     sırasında
    0.39
     noastre
    0.39
    fiées
    0.39
     étrangère
    0.38
     Vernunft
    0.38
     máscara
    0.38
    Act Density 0.011%

    No Known Activations