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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    皈
    -0.07
     PROVIDED
    -0.07
     Institute
    -0.07
     Innovative
    -0.07
     cave
    -0.06
    洄
    -0.06
    汐
    -0.06
    Extra
    -0.06
    Constraint
    -0.06
     Gör
    -0.06
    POSITIVE LOGITS
     Sears
    0.08
    enate
    0.07
     Breast
    0.07
     pierws
    0.07
    出租
    0.07
    _emit
    0.07
    的产品
    0.06
     locks
    0.06
     moons
    0.06
     polled
    0.06
    Act Density 0.035%

    No Known Activations