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

    Neuronpedia

    INDEX
    Explanations

    language related to discrimination and rights violations

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

    selective application and discrimination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.33
    蚪
    -0.31
    ۣ
    -0.30
    ANTLR
    -0.29
    withId
    -0.28
     članak
    -0.28
    śmy
    -0.28
    みた
    -0.28
     Mitarbeit
    -0.28
    leading
    -0.27
    POSITIVE LOGITS
     Targeted
    0.60
     Targeting
    0.60
     targeted
    0.59
     targeting
    0.57
     selectivity
    0.57
    تقاوى
    0.55
    Népesség
    0.53
    targeted
    0.53
     Victim
    0.53
    sele
    0.52
    Act Density 0.390%

    No Known Activations