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

    Neuronpedia

    INDEX
    Explanations

    decode

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ernest
    -0.08
     NC
    -0.08
     investment
    -0.07
    Jo
    -0.07
    "But
    -0.07
    prof
    -0.07
     Kar
    -0.07
     Prison
    -0.07
    194
    -0.07
     госп
    -0.07
    POSITIVE LOGITS
    ões
    0.07
    decoded
    0.07
     discrimination
    0.07
    NavigationItemSelectedListener
    0.06
     giải
    0.06
    需要
    0.06
     checkout
    0.06
    Offers
    0.06
     decoding
    0.06
    _only
    0.06
    Act Density 0.010%

    No Known Activations