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

    Neuronpedia

    INDEX
    Explanations

    comparative and superlative adjectives indicating degrees of quantity or quality

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

    adjectives after "more" or "most"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.42
     صوتيه
    -0.41
     gants
    -0.40
     kabát
    -0.38
     couvercle
    -0.38
     ditangkap
    -0.38
     يتيمه
    -0.36
     lanterna
    -0.35
    Autoritní
    -0.34
    paisaje
    -0.33
    POSITIVE LOGITS
     שוליים
    0.64
    //
    0.56
    dens
    0.55
    /**
    0.54
    脚注の使い方
    0.54
    endpush
    0.54
    <tbody>
    0.54
    tagHelperRunner
    0.52
    AndEndTag
    0.51
    aarrggbb
    0.50
    Act Density 0.007%

    No Known Activations