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

    Neuronpedia

    INDEX
    Explanations

    percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ilateral
    0.43
    total
    0.42
    ente
    0.41
    Amount
    0.41
    amount
    0.40
    ountain
    0.39
    ef
    0.39
    nt
    0.38
    átu
    0.38
     წინ
    0.38
    POSITIVE LOGITS
     rates
    0.40
     RETURNS
    0.38
     per
    0.37
     tour
    0.36
     carbox
    0.36
    '...
    0.35
     estou
    0.34
    ግራ
    0.34
     taught
    0.33
     बेट
    0.33
    Act Density 0.000%

    No Known Activations