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

    Neuronpedia

    INDEX
    Explanations

    the word "clear" and its variations

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

    clear adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     institution
    -0.46
    enswert
    -0.45
    idens
    -0.45
    NameInMap
    -0.44
    ditos
    -0.44
    idey
    -0.43
    tamo
    -0.43
    ụng
    -0.42
     ImageButton
    -0.42
     Sambo
    -0.42
    POSITIVE LOGITS
    Clear
    1.99
     Clear
    1.98
     CLEAR
    1.66
    CLEAR
    1.57
    clear
    1.54
     clear
    1.47
     Clears
    1.17
     Clearwater
    1.15
     clears
    1.15
     クリア
    1.07
    Act Density 0.008%

    No Known Activations