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

    Neuronpedia

    INDEX
    Explanations

    scientific evidence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     用
    -0.09
    كت
    -0.08
     Writer
    -0.08
    純
    -0.08
     Writers
    -0.08
     politely
    -0.07
     Advisor
    -0.07
     Disclaimer
    -0.07
    께
    -0.07
    poser
    -0.07
    POSITIVE LOGITS
     corrobor
    0.13
     testimon
    0.12
     beobachten
    0.11
     beob
    0.10
     surveys
    0.09
     testimony
    0.09
     calor
    0.09
    _tests
    0.09
     evidence
    0.09
    观察
    0.09
    Act Density 0.034%

    No Known Activations