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

    Neuronpedia

    INDEX
    Explanations

    expenses, costs, fees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ার
    1.46
    er
    1.45
    alang
    1.24
    aard
    1.20
    矾
    1.15
    प्रधानमंत्री
    1.13
    iune
    1.11
     спів
    1.11
    arının
    1.11
     pomeriggio
    1.11
    POSITIVE LOGITS
    з
    1.32
    ند
    1.29
    ס
    1.23
    го
    1.20
    ला
    1.16
    ల్
    1.15
    vä
    1.13
    {'
    1.13
    2
    1.13
    אר
    1.11
    Act Density 0.098%

    No Known Activations