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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -counter
    -0.06
     championship
    -0.06
    _HEADER
    -0.06
     inspected
    -0.06
     Sets
    -0.06
    公開
    -0.06
    ROC
    -0.06
     Championship
    -0.06
     upon
    -0.06
    ерше
    -0.05
    POSITIVE LOGITS
     they
    0.10
     you
    0.10
     we
    0.09
     it
    0.09
    they
    0.09
     he
    0.09
     she
    0.08
    you
    0.08
     there
    0.08
    she
    0.08
    Act Density 0.094%

    No Known Activations