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

    Neuronpedia

    INDEX
    Explanations

    code, technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fetched
    -0.06
    	task
    -0.06
    .sup
    -0.06
     fetch
    -0.06
    кур
    -0.06
     almost
    -0.06
    .lazy
    -0.06
    建設
    -0.06
     queen
    -0.06
     iteration
    -0.06
    POSITIVE LOGITS
    金
    0.07
     Shelf
    0.07
    atement
    0.07
    Beh
    0.06
    冲
    0.06
    ์ต
    0.06
    fulness
    0.06
     COMMENT
    0.06
    oglobin
    0.06
     메
    0.06
    Act Density 0.000%

    No Known Activations