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

    Neuronpedia

    INDEX
    Explanations

    Chess scores

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     воспал
    -0.07
    牌
    -0.07
    ichage
    -0.07
    озмож
    -0.06
    .Word
    -0.06
    Export
    -0.06
     gallon
    -0.06
     Samoa
    -0.06
    uspend
    -0.05
     HOT
    -0.05
    POSITIVE LOGITS
     Cheap
    0.06
    utters
    0.06
    рою
    0.06
    menu
    0.06
     worthless
    0.06
    Canon
    0.06
    ANDOM
    0.06
     issuer
    0.06
    Clean
    0.06
     з
    0.06
    Act Density 0.004%

    No Known Activations