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

    Neuronpedia

    INDEX
    Explanations

    i

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Adventure
    0.41
    樍
    0.41
    }^{*}(\
    0.39
    [](
    0.38
     इंतजार
    0.38
    日益
    0.37
    ধ
    0.37
    ┎
    0.37
     Bavarian
    0.37
    Option
    0.37
    POSITIVE LOGITS
     ligament
    0.42
    endim
    0.39
     dct
    0.38
     army
    0.37
     lis
    0.37
     каз
    0.37
     finales
    0.37
     lisa
    0.36
     nto
    0.36
     creemos
    0.36
    Act Density 0.001%

    No Known Activations