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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Fat
    -0.06
     Born
    -0.06
    ierarchical
    -0.06
    auty
    -0.06
    ).[
    -0.06
    общ
    -0.06
     editors
    -0.06
     monuments
    -0.06
     anthropology
    -0.06
    oucí
    -0.06
    POSITIVE LOGITS
     Sms
    0.07
     strtotime
    0.07
     szcz
    0.07
    エル
    0.07
     Peggy
    0.07
    !")
    0.07
    Subsystem
    0.07
     Paige
    0.06
     tweeting
    0.06
    мів
    0.06
    Act Density 0.004%

    No Known Activations