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

    Neuronpedia

    INDEX
    Explanations

    terms related to metrics, evaluation, and results in research contexts

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

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     invokingState
    -0.58
    featureID
    -0.54
     Wiktionnaire
    -0.53
    UserScript
    -0.50
    ReusableCell
    -0.47
     resourceCulture
    -0.45
    GIVEREF
    -0.45
    TagMode
    -0.43
    ´)
    -0.43
    ⎧
    -0.43
    POSITIVE LOGITS
     négoci
    0.45
     říká
    0.44
    LEGGI
    0.42
     který
    0.40
     deals
    0.40
     Tweede
    0.38
    bagno
    0.38
     Vertrags
    0.38
     handen
    0.37
     chega
    0.37
    Act Density 0.497%

    No Known Activations