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

    Neuronpedia

    INDEX
    Explanations

    like examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Other
    1.22
    Both
    1.08
    /
    1.08
     /
    1.07
    दोनों
    1.07
     altro
    1.06
     Other
    1.04
     demás
    1.02
    two
    1.02
     beiden
    1.00
    POSITIVE LOGITS
     those
    2.73
     quelli
    2.09
     celles
    1.89
    those
    1.87
     ceux
    1.87
     ours
    1.83
     thoſe
    1.80
     تلك
    1.77
     thofe
    1.71
     например
    1.69
    Act Density 0.092%

    No Known Activations