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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     immigration
    -0.07
     restriction
    -0.06
     investors
    -0.06
     elimination
    -0.06
    NotNull
    -0.06
     defeat
    -0.06
     Gaines
    -0.06
     Commands
    -0.06
     Immigration
    -0.06
     increasingly
    -0.06
    POSITIVE LOGITS
    (outputs
    0.07
     CP
    0.07
    bote
    0.06
    NDAR
    0.06
     quirky
    0.06
    념
    0.06
    　ヾ
    0.06
     cp
    0.06
    都市
    0.06
     кот
    0.06
    Act Density 0.062%

    No Known Activations