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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    енную
    -0.09
    েয়
    -0.08
    .inter
    -0.08
    .com's
    -0.08
    egenomen
    -0.08
    енной
    -0.07
    *.
    -0.07
    енная
    -0.07
    עבר
    -0.07
    ziel
    -0.07
    POSITIVE LOGITS
     voorlopig
    0.09
    割
    0.09
     pls
    0.08
     harm
    0.08
     protests
    0.08
     lawsuits
    0.08
     plut
    0.08
    گونه
    0.08
     issuance
    0.08
     danos
    0.08
    Act Density 0.029%

    No Known Activations