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

    Neuronpedia

    INDEX
    Explanations

    sets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ful
    -0.07
    @Enable
    -0.06
     Pun
    -0.06
    -square
    -0.06
     Поп
    -0.06
     Chúng
    -0.06
    Microsoft
    -0.06
     星
    -0.06
     هر
    -0.06
     Flour
    -0.06
    POSITIVE LOGITS
    cate
    0.07
    RB
    0.07
     INTER
    0.06
    .inv
    0.06
    _exist
    0.06
     sophistication
    0.06
    출장안마
    0.06
     fittings
    0.06
    tank
    0.06
    .steps
    0.06
    Act Density 0.000%

    No Known Activations