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

    Neuronpedia

    INDEX
    Explanations

    Code: Calculations/indices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ainted
    -0.06
     deputy
    -0.06
    puty
    -0.06
    odus
    -0.06
    login
    -0.06
    -di
    -0.06
     Bridges
    -0.06
     başta
    -0.06
     tráv
    -0.06
    vp
    -0.06
    POSITIVE LOGITS
     Vox
    0.07
     consenting
    0.06
     danske
    0.06
    Mutation
    0.06
    -option
    0.06
     separat
    0.06
     없는
    0.06
     conventional
    0.06
     propriet
    0.06
     Produce
    0.06
    Act Density 0.026%

    No Known Activations