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

    Neuronpedia

    INDEX
    Explanations

    x

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     WARRANTIES
    -0.07
     Day
    -0.07
    ({...
    -0.06
    -profile
    -0.06
    це
    -0.06
    %.
    -0.06
    dv
    -0.06
     kwargs
    -0.06
    din
    -0.06
     humanitarian
    -0.06
    POSITIVE LOGITS
           ↵↵
    0.07
     پاک
    0.06
    ))))
    0.06
       ↵↵
    0.06
     ó
    0.06
    Õ
    0.06
     �
    0.06
     شیمی
    0.06
     never
    0.06
     между
    0.06
    Act Density 0.083%

    No Known Activations