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

    Neuronpedia

    INDEX
    Explanations

    candidates and platforms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ROWS
    0.39
     myopia
    0.38
    旁边
    0.36
    жный
    0.36
     బ్యా
    0.35
    бата
    0.35
    ያው
    0.35
     проверить
    0.35
     लकार
    0.35
    മ്ബ
    0.35
    POSITIVE LOGITS
    。,
    0.51
    |,
    0.50
     ],
    0.46
    Copyright
    0.46
    ।,
    0.45
     |,
    0.45
    ],
    0.42
    rieved
    0.41
     ',
    0.41
     ",
    0.41
    Act Density 0.005%

    No Known Activations