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

    Neuronpedia

    INDEX
    Explanations

    common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    {}'.
    -0.07
     Centers
    -0.06
    тия
    -0.06
     Does
    -0.06
     takeover
    -0.06
     PMC
    -0.05
    ))));↵
    -0.05
    旦
    -0.05
     Spam
    -0.05
    _Is
    -0.05
    POSITIVE LOGITS
    érica
    0.07
    Eng
    0.07
     Albuquerque
    0.07
     trespass
    0.07
     �
    0.06
    وات
    0.06
    xFB
    0.06
     calf
    0.06
    /person
    0.06
    сім
    0.06
    Act Density 0.000%

    No Known Activations