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

    Neuronpedia

    INDEX
    Explanations

    bias and discrimination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Carnot
    0.43
     DMSO
    0.40
     Thermodynamic
    0.40
    ptime
    0.39
    ու
    0.39
     gadget
    0.39
     শৃ
    0.38
     Schrödinger
    0.38
     Cassini
    0.38
     moody
    0.38
    POSITIVE LOGITS
     racial
    2.08
     racially
    2.00
     racism
    1.92
     racist
    1.88
     Racial
    1.88
     Racism
    1.77
    racial
    1.71
     discriminatory
    1.55
     discrimination
    1.39
     नस्
    1.39
    Act Density 0.123%

    No Known Activations