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

    Neuronpedia

    INDEX
    Explanations

    sequences or phrases related to verification and confirmation processes

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

    French language

    np_acts-logits-general · gemini-2.0-flash

    French, Portuguese, or Russian commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArgsConstructor
    -0.54
    していますが
    -0.51
     virkelig
    -0.48
    きましたが
    -0.48
    AddTagHelper
    -0.47
     depicting
    -0.47
     nearing
    -0.47
    かれています
    -0.46
    EqualTo
    -0.45
    ovať
    -0.45
    POSITIVE LOGITS
     we
    0.69
     you
    0.69
     noDo
    0.53
     disambiguazione
    0.50
     they
    0.49
     did
    0.43
     are
    0.42
     chúng
    0.41
     would
    0.40
     have
    0.38
    Act Density 0.053%

    No Known Activations