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

    Neuronpedia

    INDEX
    Explanations

    quantitative measures and comparisons regarding various topics

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

    "How" questions

    np_acts-logits-general · gemini-2.0-flash

    how questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.56
     mukana
    -0.54
    ArrowToggle
    -0.54
     InputDecoration
    -0.52
     AppBar
    -0.51
    basicConfig
    -0.50
     TreeMap
    -0.49
     først
    -0.48
    esModule
    -0.48
    pushFollow
    -0.48
    POSITIVE LOGITS
     how
    0.60
    How
    0.58
     How
    0.56
    how
    0.50
     combien
    0.49
     HOW
    0.48
    Czy
    0.47
    Сколько
    0.47
    Jakie
    0.46
     it
    0.45
    Act Density 0.090%

    No Known Activations