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

    Neuronpedia

    INDEX
    Explanations

    document latex

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    riott
    0.40
    ediat
    0.40
    amax
    0.39
     withd
    0.38
     lag
    0.38
    hado
    0.37
     disequ
    0.37
    planned
    0.36
    lepas
    0.36
     screw
    0.36
    POSITIVE LOGITS
    ว่า
    0.47
     जाप
    0.40
    デア
    0.39
    美好的
    0.38
    承
    0.38
    带来了
    0.37
     préférences
    0.35
    Marian
    0.35
     ],"
    0.34
    㧡
    0.34
    Act Density 0.000%

    No Known Activations