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

    Neuronpedia

    INDEX
    Explanations

    Malvolio, Mavalli, Mirvac

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    К
    1.35
    .
    1.29
    у
    1.26
    其他
    1.10
     conglomerates
    1.07
     aluno
    1.06
    ر
    1.05
    ड
    1.05
     טוב
    1.02
     edificios
    1.00
    POSITIVE LOGITS
    am
    2.05
    9
    1.57
    6
    1.38
    on
    1.36
    2
    1.33
    as
    1.29
    0
    1.29
    ↵↵
    1.28
    in
    1.24
    or
    1.23
    Act Density 0.000%

    No Known Activations