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

    Neuronpedia

    INDEX
    Explanations

    space

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sebuah
    -0.06
     zahl
    -0.06
    .Batch
    -0.06
     Yer
    -0.06
     stopwords
    -0.06
     eaten
    -0.06
     деся
    -0.06
    ViewInit
    -0.06
     círk
    -0.06
     Reyn
    -0.05
    POSITIVE LOGITS
    ophysical
    0.07
     relative
    0.07
    adm
    0.07
     University
    0.07
     Sailor
    0.07
     submerged
    0.07
    lex
    0.06
     interacts
    0.06
    spaces
    0.06
     didnt
    0.06
    Act Density 0.006%

    No Known Activations