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

    Neuronpedia

    INDEX
    Explanations

    ui button creation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    C
    0.71
    PI
    0.70
    Title
    0.62
    Ak
    0.62
    0
    0.62
    Back
    0.61
    Dw
    0.61
    Cl
    0.61
    Art
    0.61
    N
    0.61
    POSITIVE LOGITS
     eventuali
    0.66
     erstellen
    0.61
     troubleshoot
    0.61
     usability
    0.60
     {};
    0.59
     initializing
    0.58
     debugging
    0.58
     decrement
    0.57
    .';
    0.57
     innebär
    0.57
    Act Density 0.002%

    No Known Activations