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

    Neuronpedia

    INDEX
    Explanations

    references to divisions and separations

    oai_token-act-pair · gemini-2.0-flash

    separate or own

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الحره
    -1.34
     EconPapers
    -1.17
     raiſ
    -1.15
     Efq
    -1.09
    contentLoaded
    -1.09
     otomatig
    -1.08
     myſelf
    -1.06
     CreateTagHelper
    -1.01
     houſe
    -0.98
    ImageContext
    -0.98
    POSITIVE LOGITS
     
    0.56
     K
    0.47
    -
    0.46
    ,
    0.46
     New
    0.45
     r
    0.44
    .
    0.44
     k
    0.43
     C
    0.43
     P
    0.42
    Act Density 1.606%

    No Known Activations