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

    Neuronpedia

    INDEX
    Explanations

    statements reflecting denial or rejection of accusations

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

    Preceding auxiliary verbs

    np_acts-logits-general · gemini-2.0-flash

    technical terms or technical descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ("]");
    -0.57
     lenker
    -0.56
     raras
    -0.53
     suministros
    -0.53
     vides
    -0.50
    >--}}
    -0.49
     Needles
    -0.49
     seper
    -0.49
     financieras
    -0.49
     científicas
    -0.49
    POSITIVE LOGITS
     contemplates
    0.65
    VersionUID
    0.63
    GenerationType
    0.62
    ºC
    0.61
     incipient
    0.60
     NSCoder
    0.60
    awtextra
    0.59
     proposal
    0.59
     supposes
    0.59
    ThroughAttribute
    0.58
    Act Density 0.559%

    No Known Activations