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

    Neuronpedia

    INDEX
    Explanations

    Showing Up for Racial Justice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     сфор
    0.42
     उछ
    0.41
     amené
    0.41
    馁
    0.40
    िकुलर
    0.39
     ойно
    0.39
    πει
    0.39
     यार
    0.39
     হইয়৷
    0.39
     solicitado
    0.39
    POSITIVE LOGITS
    जम
    0.37
    MACH
    0.36
    Venue
    0.34
    同步
    0.34
    imba
    0.34
    優
    0.33
     empathy
    0.33
    短期
    0.33
     никакого
    0.33
    分享
    0.33
    Act Density 0.001%

    No Known Activations