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

    Neuronpedia

    INDEX
    Explanations

    general business writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     medicine
    -0.08
     �
    -0.07
     endorsements
    -0.07
     Nurs
    -0.07
     Medium
    -0.07
     grave
    -0.07
    lift
    -0.07
     收
    -0.07
     killings
    -0.06
    -ag
    -0.06
    POSITIVE LOGITS
     kneeling
    0.07
     klid
    0.06
     Lands
    0.06
    !!!↵↵
    0.06
     "}\
    0.06
    _reports
    0.06
    _vertical
    0.06
     kıy
    0.06
     vyž
    0.06
     CPPUNIT
    0.06
    Act Density 0.000%

    No Known Activations