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

    Neuronpedia

    INDEX
    Explanations

    conversations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ro
    -0.07
     органів
    -0.07
    우스
    -0.06
    채
    -0.06
    ilateral
    -0.06
     واب
    -0.06
     minimalist
    -0.06
    sp
    -0.06
     поверх
    -0.06
    _flight
    -0.06
    POSITIVE LOGITS
     })(
    0.07
    О
    0.06
    termination
    0.06
    ]:
    0.06
    だから
    0.06
     où
    0.06
    灣
    0.06
     assured
    0.06
    Jacob
    0.06
    Am
    0.06
    Act Density 0.011%

    No Known Activations