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

    Neuronpedia

    INDEX
    Explanations

    expressions related to user profiles and errors

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

    Malay and Slovenian words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IContainer
    -0.66
     AssemblyCompany
    -0.62
    ChildScrollView
    -0.61
    énario
    -0.59
     betweenstory
    -0.56
     فريبيس
    -0.56
    脚注の使い方
    -0.55
     ब्रेकडाउन
    -0.55
    󠁴
    -0.54
     AllAfrica
    -0.54
    POSITIVE LOGITS
     ikkje
    0.48
    xase
    0.47
    bibfield
    0.44
     sœurs
    0.43
     utilised
    0.42
     practising
    0.41
    ể
    0.40
     pelbagai
    0.39
     peores
    0.38
     utilising
    0.38
    Act Density 0.012%

    No Known Activations