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

    Neuronpedia

    INDEX
    Explanations

    less

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grapes
    -0.07
    ado
    -0.06
     mereka
    -0.06
     Sche
    -0.06
     ese
    -0.06
     plav
    -0.06
     แล
    -0.06
     yapılacak
    -0.06
     donner
    -0.06
    orange
    -0.06
    POSITIVE LOGITS
     집
    0.07
    .Cryptography
    0.07
    ？
    0.07
    ATFORM
    0.07
    -under
    0.06
    ibrated
    0.06
    (ok
    0.06
    “,
    0.06
    μβρίου
    0.06
     ['$
    0.06
    Act Density 0.002%

    No Known Activations