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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significance or popularity in various contexts

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

    "One of the"

    np_acts-logits-general · gemini-2.0-flash

    one of the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vœux
    -0.76
     épaules
    -0.72
     genoux
    -0.69
     attentes
    -0.69
     lèvres
    -0.67
     âmes
    -0.67
     version
    -0.66
     émotions
    -0.62
     pouvoirs
    -0.60
     counterpart
    -0.59
    POSITIVE LOGITS
     many
    0.67
     earliest
    0.65
    many
    0.65
     nahilalakip
    0.65
     tantos
    0.63
    ApiModelProperty
    0.61
     tanti
    0.59
     MANY
    0.59
    MANY
    0.58
     tantas
    0.58
    Act Density 0.184%

    No Known Activations