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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "highly" and its variations

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

    Follows "highly"

    np_acts-logits-general · gemini-2.0-flash

    highly + adjective/adverb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     entirely
    -0.65
     pleinement
    -0.64
     very
    -0.62
     aveug
    -0.59
     wholly
    -0.59
     langt
    -0.59
     énorme
    -0.58
     heureuse
    -0.56
     completely
    -0.56
     large
    -0.55
    POSITIVE LOGITS
     nakalista
    0.74
    IntoConstraints
    0.72
     regarded
    0.64
    ">—
    0.60
    HtmlAttribute
    0.58
     snippetHide
    0.57
    InitStruct
    0.56
    ungkinan
    0.56
    Likely
    0.55
     indebted
    0.55
    Act Density 0.114%

    No Known Activations