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

    Neuronpedia

    INDEX
    Explanations

    log following quote

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queim
    0.48
     wealthy
    0.46
     ತೋರಿಸ
    0.45
     aggrieved
    0.45
     aggrav
    0.43
     sogg
    0.43
     feit
    0.43
     dangerous
    0.42
     positivas
    0.42
     drivers
    0.42
    POSITIVE LOGITS
    世纪
    0.50
    !)
    0.46
    。）
    0.46
    ।)
    0.46
    Creating
    0.44
     भव्य
    0.44
    ৷
    0.44
    梼
    0.44
    École
    0.44
     Biomedical
    0.43
    Act Density 0.003%

    No Known Activations