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

    Neuronpedia

    INDEX
    Explanations

    programming language identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    …,
    1.22
     siitä
    1.22
    /-}$
    1.22
    ->"
    1.20
     leukocyte
    1.20
    ¹,
    1.19
     ',',
    1.18
     ",",
    1.17
     없고
    1.16
     não
    1.16
    POSITIVE LOGITS
    ↵
    1.54
            
    1.18
    ↵↵
    1.11
     delighted
    1.10
    ↵↵↵
    1.10
    fyp
    1.07
    );
    1.06
    ForeColor
    1.05
           
    1.04
          
    1.01
    Act Density 0.307%

    No Known Activations