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

    Neuronpedia

    INDEX
    Explanations

    formulas and charts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Advertising
    0.45
     advertising
    0.43
     compte
    0.41
    advertise
    0.40
    kids
    0.40
    comps
    0.40
    advertising
    0.39
    addAction
    0.39
     باست
    0.38
     klad
    0.38
    POSITIVE LOGITS
     formula
    0.59
     formulas
    0.55
     chart
    0.53
    formula
    0.52
     formulae
    0.49
     ramifications
    0.49
    Formula
    0.47
     debacle
    0.47
     चार्ट
    0.46
     формула
    0.45
    Act Density 0.000%

    No Known Activations