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

    Neuronpedia

    INDEX
    Explanations

    Business-related text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .thumbnail
    -0.07
    	vm
    -0.07
    焘
    -0.07
     XIII
    -0.07
    (File
    -0.06
    oxide
    -0.06
     PEM
    -0.06
    .waitFor
    -0.06
    stellung
    -0.06
    	im
    -0.06
    POSITIVE LOGITS
    最关键
    0.07
    を利用する
    0.07
    .blogspot
    0.07
    갰
    0.06
    Squared
    0.06
    isnan
    0.06
     équipé
    0.06
     BY
    0.06
    ERC
    0.06
    紊乱
    0.06
    Act Density 0.132%

    No Known Activations