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

    Neuronpedia

    INDEX
    Explanations

    code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     users
    0.71
     options
    0.64
     services
    0.60
     if
    0.59
     validator
    0.59
     such
    0.59
     encapsulates
    0.58
     modus
    0.57
     옵
    0.57
     option
    0.56
    POSITIVE LOGITS
    маш
    0.64
    šu
    0.64
    ishments
    0.63
    Area
    0.63
    ത്താ
    0.63
    веду
    0.63
    hibited
    0.61
    क्षर
    0.60
    iterranean
    0.59
    ვით
    0.59
    Act Density 0.000%

    No Known Activations