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

    Neuronpedia

    INDEX
    Explanations

    instances of Japanese text that express questions or requests for clarification

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

    talking about people and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IsMutable
    -0.68
     miniaturka
    -0.63
     Wikiseite
    -0.60
     myſelf
    -0.60
     wikipagina
    -0.58
    ConstraintMaker
    -0.58
    ſelves
    -0.57
     препратки
    -0.56
     itſelf
    -0.55
    MigrationBuilder
    -0.54
    POSITIVE LOGITS
    ༘
    0.33
    RTLD
    0.32
     SV
    0.31
    Hentet
    0.31
     unit
    0.31
    back
    0.30
    HD
    0.30
     Hin
    0.30
    ണ
    0.30
    വാ
    0.29
    Act Density 0.033%

    No Known Activations