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
     natürlich
    -0.08
     menggunakan
    -0.07
    .BL
    -0.07
     Freund
    -0.06
     виду
    -0.06
    �
    -0.06
     yıllarda
    -0.06
    чих
    -0.06
    !\
    -0.06
     Gors
    -0.06
    POSITIVE LOGITS
    configured
    0.08
    ictures
    0.07
     extending
    0.07
     climbing
    0.06
    losing
    0.06
     preference
    0.06
     eating
    0.06
    _PRIMARY
    0.06
     catalogue
    0.06
    ịch
    0.06
    Act Density 0.071%

    No Known Activations