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

    Neuronpedia

    INDEX
    Explanations

    expressions of admiration or being impressed

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

    expression of being impressed or admired

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gynhyrchwyd
    -0.42
    ChildScrollView
    -0.40
     CreateTagHelper
    -0.39
    indelijk
    -0.36
    ScopeManager
    -0.34
    endsection
    -0.32
     gebe
    -0.30
     eventually
    -0.30
    <![
    -0.30
    UnusedPrivate
    -0.30
    POSITIVE LOGITS
     admirer
    0.62
     admiration
    0.59
     protoimpl
    0.57
     impressed
    0.54
    writeFieldEnd
    0.54
    reciate
    0.52
     admires
    0.51
     admire
    0.50
     Appreciate
    0.49
     Attraction
    0.48
    Act Density 0.052%

    No Known Activations