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

    Neuronpedia

    INDEX
    Explanations

    sexist

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IIUM
    0.36
    AE
    0.36
    INavigation
    0.35
    enchymal
    0.35
    anter
    0.34
    cina
    0.34
    $-[
    0.34
     Cavalry
    0.34
     Palo
    0.33
    屠
    0.33
    POSITIVE LOGITS
    radioButton
    0.36
    MEGA
    0.35
     robbery
    0.34
    Companion
    0.34
     Sas
    0.34
     Le
    0.34
    sab
    0.34
     robert
    0.33
     रॉबर्ट
    0.33
     Sab
    0.33
    Act Density 0.013%

    No Known Activations