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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to results and findings in research

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

    demonstratedrevealedindicateforbyboth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.53
    évaluateur
    -0.46
    httphttps
    -0.45
     CanadaChoose
    -0.45
    ỡng
    -0.43
     blauwe
    -0.42
    PYX
    -0.40
     <>",
    -0.40
     архивлан
    -0.39
    tagHelperRunner
    -0.38
    POSITIVE LOGITS
    liothèque
    0.49
     насељу
    0.45
     BnF
    0.43
    الحياه
    0.43
    すべて
    0.42
     alles
    0.41
     lleve
    0.40
    ürnberg
    0.40
     everything
    0.40
    convergence
    0.39
    Act Density 0.393%

    No Known Activations