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

    Neuronpedia

    INDEX
    Explanations

    spreadsheet formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    预览
    -0.07
     ihrem
    -0.06
    誠
    -0.06
    ürger
    -0.06
    .IM
    -0.06
     cân
    -0.06
     paramMap
    -0.06
    Al
    -0.06
     střed
    -0.06
    ところ
    -0.06
    POSITIVE LOGITS
     Movement
    0.07
     technically
    0.07
    **/↵↵
    0.07
    τια
    0.06
    liquid
    0.06
    -Length
    0.06
    _oc
    0.06
    ansk
    0.06
    ISTRY
    0.06
    ATALOG
    0.06
    Act Density 0.002%

    No Known Activations