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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating suitability and budget considerations

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

    Preceding numbers or symbols

    np_acts-logits-general · gemini-2.0-flash

    yet followed by contrast or specification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.76
    ']){
    -0.68
    ¬
    -0.64
    ')){
    -0.64
     createState
    -0.56
     »,
    -0.53
    "){
    -0.51
    ､
    -0.51
       
    -0.51
    ‑
    -0.50
    POSITIVE LOGITS
    --
    0.71
     civils
    0.68
    dafx
    0.65
     مرئيه
    0.64
    --$
    0.63
    "--
    0.63
    --"
    0.62
    '--
    0.61
     sagesse
    0.59
    &
    0.57
    Act Density 0.072%

    No Known Activations