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

    Neuronpedia

    INDEX
    Explanations

    webpack

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tonne
    0.42
    这也是
    0.40
    可以
    0.39
    ∬
    0.38
    ('|
    0.37
    ATIONAL
    0.37
    Hispanic
    0.36
    ITIONAL
    0.36
    lstm
    0.36
    ડા
    0.36
    POSITIVE LOGITS
     brakes
    0.54
     prévu
    0.52
     Ці
    0.47
     jiwa
    0.46
     roti
    0.46
     vieron
    0.46
     hongos
    0.46
     diuretics
    0.46
     Supplements
    0.46
     Cricket
    0.45
    Act Density 0.007%

    No Known Activations