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

    Neuronpedia

    INDEX
    Explanations

    specific conditions or situations that indicate factors leading to system errors or performance issues

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

    conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -0.39
     auprès
    -0.39
     caballeros
    -0.37
     
    -0.36
     Defensa
    -0.33
    empêcher
    -0.33
    นัก
    -0.32
     çiz
    -0.32
     Herausforderung
    -0.32
     celebración
    -0.32
    POSITIVE LOGITS
     виправивши
    0.68
     or
    0.61
    hyrchwyd
    0.61
     или
    0.57
     hoặc
    0.57
     Paglinawan
    0.56
    或者
    0.56
    AddHtmlAttribute
    0.55
     Italijani
    0.54
    ſicht
    0.53
    Act Density 0.050%

    No Known Activations