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

    Neuronpedia

    INDEX
    Explanations

    phrases or concepts that indicate clarity or transparency

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

    clear enough

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onson
    -0.60
     Fod
    -0.56
    ingdon
    -0.51
     Mousse
    -0.51
     AssemblyProduct
    -0.51
     Abingdon
    -0.50
    bitan
    -0.50
    LLocation
    -0.50
     Վերցված
    -0.49
     Moto
    -0.49
    POSITIVE LOGITS
     clear
    1.94
    clear
    1.80
     Clear
    1.74
    Clear
    1.73
     CLEAR
    1.48
    CLEAR
    1.38
     clears
    1.26
     chiaro
    1.19
     clearer
    1.16
     claras
    1.16
    Act Density 0.021%

    No Known Activations