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

    Neuronpedia

    INDEX
    Explanations

    symbols introducing code or output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    јан
    0.37
     hongos
    0.37
    ٹا
    0.36
    美品
    0.36
     citoyens
    0.36
     voyageurs
    0.35
     bonnes
    0.35
     tiež
    0.35
     Saltar
    0.34
    ڑا
    0.34
    POSITIVE LOGITS
    inser
    0.36
    {
    0.35
    s
    0.33
    lag
    0.33
    end
    0.32
    loss
    0.31
    {\
    0.31
    includegraphics
    0.31
    The
    0.31
    änz
    0.31
    Act Density 0.100%

    No Known Activations