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

    Neuronpedia

    INDEX
    Explanations

    expressions of negative commands or denials in conversations

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

    conversational phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.58
     disambiguazione
    -0.57
    tagHelperRunner
    -0.52
     Pemer
    -0.49
    bootstrapcdn
    -0.47
    rungsseite
    -0.47
    AndEndTag
    -0.46
    TypedDataSet
    -0.44
     yyj
    -0.43
     Rhiz
    -0.43
    POSITIVE LOGITS
     Administrativna
    0.44
     SwitchCompat
    0.40
    HttpDelete
    0.40
    makeText
    0.40
     HttpNotFound
    0.39
    Obrázky
    0.37
    ,"
    0.37
    HttpPut
    0.36
     Extragalactic
    0.36
    Diwedd
    0.36
    Act Density 0.031%

    No Known Activations