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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a variety or diversity of options

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

    wide range of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TemporalType
    -0.45
    addComponent
    -0.39
     Comunicação
    -0.39
     ekster
    -0.39
    postsleuth
    -0.39
    zeitige
    -0.38
    Zunanje
    -0.38
    nloa
    -0.37
    PropertyChanging
    -0.37
     republi
    -0.37
    POSITIVE LOGITS
     range
    0.93
     variety
    0.71
     Range
    0.69
     wide
    0.69
     RANGE
    0.65
     ranges
    0.64
    range
    0.64
    Range
    0.63
     spectrum
    0.62
     diverse
    0.62
    Act Density 0.115%

    No Known Activations