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

    Neuronpedia

    INDEX
    Explanations

    regulatory compliance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ※
    0.40
    {,}
    0.38
     annulus
    0.38
    ♪
    0.38
     keputusan
    0.37
    ^)
    0.37
     Similar
    0.37
    §
    0.37
    ImageBox
    0.36
     mittels
    0.36
    POSITIVE LOGITS
     submenu
    0.41
    uring
    0.41
    접
    0.40
    eting
    0.39
    éseket
    0.39
    चर्स
    0.39
    partisan
    0.39
    phon
    0.38
    energy
    0.38
    past
    0.38
    Act Density 0.000%

    No Known Activations