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

    Neuronpedia

    INDEX
    Explanations

    variable assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     உலோக
    0.30
    ሳሪያ
    0.27
    ತಕ್ಕ
    0.27
    疾患
    0.26
    utiérrez
    0.26
    कोलॉजी
    0.26
    髂
    0.26
     எல்லா
    0.25
     रिचार्ज
    0.25
     ಮಾಹಿತ
    0.25
    POSITIVE LOGITS
    -
    0.40
     (
    0.36
    :
    0.35
    /
    0.35
     and
    0.34
    _
    0.34
    +
    0.33
    ↵
    0.32
    ات
    0.32
    =
    0.32
    Act Density 0.242%

    No Known Activations