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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with scientific investigation and research findings

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

    after certain prepositions or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    realized, occurred, actual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tembelea
    -0.64
    Cyfarwyddwr
    -0.46
     дописавши
    -0.44
    ********/
    -0.42
     CanadaChoose
    -0.42
    AndEndTag
    -0.41
    *****/
    -0.41
    %";
    -0.40
    '])->
    -0.40
    /***/
    -0.39
    POSITIVE LOGITS
    fillment
    0.46
     Realität
    0.42
     realisation
    0.42
     comply
    0.42
     complying
    0.42
     speł
    0.41
    compliant
    0.41
    符合
    0.40
    quelize
    0.40
     Erfüllung
    0.40
    Act Density 0.982%

    No Known Activations