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

    Neuronpedia

    INDEX
    Explanations

    respectful professional tone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    odem
    0.46
    ً
    0.45
    rg
    0.44
    ]
    0.44
    ara
    0.42
    >/
    0.40
     áng
    0.40
     запу
    0.40
    弥
    0.39
    ra
    0.39
    POSITIVE LOGITS
     multiv
    0.45
     nix
    0.45
    が一
    0.45
    անդ
    0.44
    ೌ
    0.44
     comedy
    0.43
     STILL
    0.43
     HUNT
    0.43
     crush
    0.42
     Reve
    0.42
    Act Density 0.000%

    No Known Activations