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

    Neuronpedia

    INDEX
    Explanations

    Repetitive instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ратить
    -0.08
     hollywood
    -0.08
     camis
    -0.08
     印
    -0.07
    რაფ
    -0.07
     Kaya
    -0.07
    עדיע
    -0.07
    ljive
    -0.07
    afima
    -0.07
    资料
    -0.07
    POSITIVE LOGITS
    Manual
    0.08
     manual
    0.08
    Orient
    0.07
     manu
    0.07
    Conf
    0.07
     Manual
    0.07
    Planet
    0.07
    matches
    0.07
     Oriental
    0.07
    Listing
    0.07
    Act Density 0.002%

    No Known Activations