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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    เฟ
    -0.07
     Terrace
    -0.07
    ral
    -0.06
     deterioration
    -0.06
    анных
    -0.06
    到底
    -0.06
    么
    -0.06
    components
    -0.06
     Plenty
    -0.06
     buyers
    -0.06
    POSITIVE LOGITS
    �
    0.07
    inscription
    0.06
     difficile
    0.06
    �
    0.06
    john
    0.06
    .ignore
    0.06
    (dl
    0.06
    _SM
    0.06
     ke
    0.06
     m�
    0.06
    Act Density 0.009%

    No Known Activations