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
     излож
    -0.08
     सु
    -0.08
    تری
    -0.08
    impi
    -0.08
    _seg
    -0.08
     след
    -0.07
     समुदाय
    -0.07
    _double
    -0.07
     developed
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    ınıza
    0.09
     someplace
    0.09
     Hooks
    0.09
     somewhere
    0.09
     Wherever
    0.09
     вашего
    0.08
     preferably
    0.08
     вашем
    0.08
     declara
    0.08
     rẹ
    0.08
    Act Density 0.016%

    No Known Activations