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

    Neuronpedia

    INDEX
    Explanations

    elements related to ratings and classifications

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

    similarity or continuation

    np_acts-logits-general · gemini-2.0-flash

    similarity or another

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -0.68
     totiž
    -0.61
     derfor
    -0.61
     namelijk
    -0.60
     anyway
    -0.58
    endphp
    -0.57
    それが
    -0.55
    annique
    -0.55
    #![
    -0.54
    Ведь
    -0.52
    POSITIVE LOGITS
     ebenfalls
    2.04
     similarly
    1.78
    another
    1.75
     another
    1.74
    Another
    1.64
     szint
    1.61
    こちらも
    1.61
    ditto
    1.58
     Another
    1.55
     likewise
    1.54
    Act Density 0.978%

    No Known Activations