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

    Neuronpedia

    INDEX
    Explanations

    legal citations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =>'
    -0.07
    Cancel
    -0.07
    最容易
    -0.07
     unfinished
    -0.07
     crush
    -0.06
    (suffix
    -0.06
    [file
    -0.06
    不属于
    -0.06
    Href
    -0.06
     Stefan
    -0.06
    POSITIVE LOGITS
     mechanics
    0.07
     processing
    0.07
    שת
    0.07
    با
    0.07
    lector
    0.06
     olduğu
    0.06
    經驗
    0.06
     contradiction
    0.06
    ona
    0.06
     tanto
    0.06
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.