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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reversible
    0.79
    衡
    0.74
    managerpage
    0.70
     passado
    0.68
    jx
    0.68
    Curves
    0.68
     passport
    0.68
     quarries
    0.68
    छा
    0.67
     ازاي
    0.67
    POSITIVE LOGITS
    ̄
    0.62
    mē
    0.58
    ಿನ
    0.57
    了大
    0.57
     Liter
    0.55
     Resource
    0.55
     var
    0.54
     hmot
    0.54
    স্র
    0.54
     Garland
    0.53
    Act Density 0.005%

    No Known Activations