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

    Neuronpedia

    INDEX
    Explanations

    C++ code generation tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     divisão
    0.49
    Continent
    0.48
    مد
    0.48
    王国
    0.43
    CriteriaUtils
    0.43
    ضا
    0.43
     đỏ
    0.42
    ；
    0.42
     Farb
    0.41
     chutes
    0.41
    POSITIVE LOGITS
    iostream
    0.54
    i
    0.52
    ib
    0.47
    ill
    0.46
     fmt
    0.46
     Professionals
    0.46
     Інтэр
    0.46
    $\--
    0.46
    x
    0.45
    ith
    0.44
    Act Density 0.014%

    No Known Activations