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

    Neuronpedia

    INDEX
    Explanations

    negative sentiment or unfavorable outcomes

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

    Numbers following hyphens

    np_acts-logits-general · gemini-2.0-flash

    numbers after 'ago'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Portale
    -0.58
    :
    -0.50
     dru
    -0.50
    .
    -0.49
     luci
    -0.48
    führt
    -0.46
     الاطلاع
    -0.45
     Lehre
    -0.45
     saj
    -0.45
    above
    -0.44
    POSITIVE LOGITS
    ंदीखरीदारी
    0.77
    enumi
    0.77
    IntoConstraints
    0.70
    MessageOf
    0.67
    NUMX
    0.66
     mohair
    0.60
     originais
    0.60
    <bos>
    0.59
     AssemblyCompany
    0.57
     Audiodateien
    0.57
    Act Density 0.042%

    No Known Activations