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

    Neuronpedia

    INDEX
    Explanations

    often focuses on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     amusing
    0.43
    မျှ
    0.41
    ాత్ర
    0.41
    及ひ
    0.40
    詑
    0.40
    ottam
    0.40
    of
    0.39
     کی
    0.39
    を楽しむ
    0.39
     draught
    0.39
    POSITIVE LOGITS
    塞
    0.42
     detalles
    0.42
     nero
    0.40
     semillas
    0.40
     nered
    0.40
     fue
    0.39
     negras
    0.39
     Ansatz
    0.39
    ╼
    0.39
     byl
    0.38
    Act Density 0.007%

    No Known Activations