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

    Neuronpedia

    INDEX
    Explanations

    he or she

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Testing
    -0.07
    거나
    -0.06
    _cos
    -0.06
     organizational
    -0.06
    overnment
    -0.06
     Deposit
    -0.06
    üc
    -0.06
     Uri
    -0.06
     Comic
    -0.06
     regional
    -0.06
    POSITIVE LOGITS
    姿
    0.06
    하
    0.06
     He
    0.06
     Poke
    0.06
    х
    0.06
    heets
    0.06
     he
    0.06
    ßer
    0.06
    ylation
    0.06
    pel
    0.06
    Act Density 0.035%

    No Known Activations