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

    Neuronpedia

    INDEX
    Explanations

    PHP namespaces and use statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ্যাথ
    0.41
    ቕ
    0.38
    䚰
    0.38
    喈
    0.37
     saque
    0.37
     mutagenesis
    0.36
    elics
    0.36
    0.36
    ikiem
    0.35
    Фран
    0.35
    POSITIVE LOGITS
     Illuminate
    0.77
    Illuminate
    0.76
     std
    0.65
     Symfony
    0.61
    std
    0.58
    Symfony
    0.55
     illuminate
    0.54
     Illumin
    0.49
     League
    0.46
     illuminating
    0.46
    Act Density 0.001%

    No Known Activations