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

    Neuronpedia

    INDEX
    Explanations

    etc

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MER
    -0.07
    쉔
    -0.07
     screw
    -0.07
    _CHAIN
    -0.07
    .column
    -0.07
     Discount
    -0.07
    -spin
    -0.07
    流水
    -0.07
     Inventory
    -0.07
     Ble
    -0.07
    POSITIVE LOGITS
     Gdańsk
    0.07
    有任何
    0.07
     equalTo
    0.07
     regularly
    0.07
     forgiving
    0.07
     آخر
    0.07
     באזור
    0.07
    .Ignore
    0.07
    .out
    0.07
     UNKNOWN
    0.07
    Act Density 0.004%

    No Known Activations