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

    Neuronpedia

    INDEX
    Explanations

    also

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ьем
    -0.07
     insuff
    -0.07
     العالية
    -0.07
     другом
    -0.07
    ती
    -0.07
     fairly
    -0.07
    �
    -0.07
     assurances
    -0.07
    קע
    -0.07
     طول
    -0.07
    POSITIVE LOGITS
    Complement
    0.08
     Complement
    0.08
    들을
    0.08
    chak
    0.08
     complementar
    0.08
    .lon
    0.07
    (typeof
    0.07
     complement
    0.07
     complementary
    0.07
     Lane
    0.07
    Act Density 0.005%

    No Known Activations