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

    Neuronpedia

    INDEX
    Explanations

    ，要

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     excuses
    -0.08
    dbc
    -0.08
    .this
    -0.08
     awkward
    -0.08
    Dining
    -0.07
    Rates
    -0.07
    Handled
    -0.07
     kase
    -0.07
    Rocket
    -0.07
     ovog
    -0.07
    POSITIVE LOGITS
     ಕಥ
    0.09
    улат
    0.08
    ologic
    0.08
     ಕುರ
    0.08
    ದಿಂದ
    0.07
    ‌ನ
    0.07
     ಮೂಲ
    0.07
     рассказы
    0.07
     прилож
    0.07
     ಒ
    0.07
    Act Density 0.045%

    No Known Activations