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

    Neuronpedia

    INDEX
    Explanations

    expression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dangers
    -0.07
    _utc
    -0.07
     diabetes
    -0.07
    [cnt
    -0.06
    戰
    -0.06
     Det
    -0.06
     EDIT
    -0.06
    552
    -0.06
     pandemic
    -0.06
     sea
    -0.06
    POSITIVE LOGITS
     expressed
    0.11
     expressing
    0.10
     expresses
    0.10
     express
    0.09
     expression
    0.09
     Expression
    0.08
     expressions
    0.08
     กร
    0.08
    Expression
    0.08
    .Expression
    0.08
    Act Density 0.035%

    No Known Activations