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

    Neuronpedia

    INDEX
    Explanations

    generating text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dé
    0.38
    blick
    0.37
     অবশেষে
    0.37
    ...",
    0.37
     (\
    0.37
     Bootstrap
    0.37
     licenc
    0.36
     Vieux
    0.36
     Perp
    0.36
    flowLayoutPanel
    0.36
    POSITIVE LOGITS
    想法
    0.40
    перы
    0.39
    完整
    0.38
    ottest
    0.38
    免费
    0.38
    irting
    0.38
    ANGER
    0.37
    THING
    0.37
    PLO
    0.37
    akl
    0.37
    Act Density 0.026%

    No Known Activations