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

    Neuronpedia

    INDEX
    Explanations

    concepts related to negation and the questioning of beliefs or perceptions

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

    not care

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.86
    httphttps
    -0.59
    AndEndTag
    -0.56
    Referencies
    -0.52
     ویکی‌آمباردا
    -0.49
    ValueStyle
    -0.48
     calendriers
    -0.47
    berdayakan
    -0.47
    ambién
    -0.47
    -0.45
    POSITIVE LOGITS
    ness
    0.48
    QUA
    0.45
    NESS
    0.39
    nesses
    0.38
    transQ
    0.36
    siya
    0.36
     hatred
    0.36
    esses
    0.35
    Non
    0.35
     المعل
    0.35
    Act Density 0.152%

    No Known Activations