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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty and negation in discourse

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

    Dutch words and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enumii
    -0.49
     defaultstate
    -0.47
    Ӕ
    -0.38
    bootstrapcdn
    -0.38
    "?>
    -0.35
     springfox
    -0.34
    roots
    -0.33
    -0.33
     Numerade
    -0.33
     oble
    -0.33
    POSITIVE LOGITS
     unfair
    0.49
     mijne
    0.48
    isContained
    0.47
     wikipagina
    0.47
    tonode
    0.47
     zoude
    0.47
    keyColumn
    0.45
     donker
    0.45
     praktijk
    0.45
     vrijwilli
    0.44
    Act Density 0.200%

    No Known Activations