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

    Neuronpedia

    INDEX
    Explanations

    fiscal years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ীষ্ম
    0.25
     ingrédients
    0.24
     deformations
    0.24
    🫡
    0.23
     hydrolysis
    0.22
     oxidación
    0.22
    尴
    0.22
     cyclohex
    0.22
    酛
    0.22
     $\%$
    0.22
    POSITIVE LOGITS
    C
    0.26
    http
    0.26
    s
    0.25
    G
    0.25
    d
    0.25
    T
    0.25
    S
    0.24
    www
    0.23
    {
    0.23
    D
    0.22
    Act Density 0.001%

    No Known Activations