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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and specific names, particularly those related to people or entities

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

    sockets and networking contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     give
    -0.36
     regimes
    -0.32
    itschrift
    -0.31
     باخ
    -0.30
    ลง
    -0.29
    ţin
    -0.29
    bisoft
    -0.29
    bleau
    -0.29
     Meek
    -0.28
     Москву
    -0.28
    POSITIVE LOGITS
    niſſe
    0.62
    ConstraintMaker
    0.59
     CreateTagHelper
    0.57
     Geſch
    0.56
     transfieras
    0.55
    transQ
    0.55
     nahilalakip
    0.55
     nakalista
    0.54
     AssemblyCompany
    0.53
    ьаж
    0.53
    Act Density 0.003%

    No Known Activations