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

    Neuronpedia

    INDEX
    Explanations

    dialogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     systému
    -0.07
    Bir
    -0.07
     toaster
    -0.06
     LIFE
    -0.06
    .Pattern
    -0.06
    VAL
    -0.06
     Life
    -0.06
    Bei
    -0.06
    SP
    -0.06
    组
    -0.05
    POSITIVE LOGITS
    reet
    0.07
    >Hello
    0.07
     #__
    0.07
     foliage
    0.06
    coon
    0.06
    rvine
    0.06
    :CGPoint
    0.06
    ##_
    0.06
    signed
    0.06
    −
    0.06
    Act Density 0.017%

    No Known Activations