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

    Neuronpedia

    INDEX
    Explanations

    official investigations and reports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spacetime
    0.73
     badass
    0.73
     সর্বদা
    0.73
     এই
    0.72
     Metaverse
    0.71
     యొక్క
    0.71
     traversal
    0.70
     podrás
    0.70
     minimalistic
    0.70
     whilst
    0.69
    POSITIVE LOGITS
     spokeswoman
    0.65
     statewide
    0.64
     spokesman
    0.64
    棉
    0.57
     ત્રણ
    0.57
     staffers
    0.57
     officials
    0.57
     federally
    0.57
    抖
    0.56
     पांच
    0.55
    Act Density 0.007%

    No Known Activations