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

    Neuronpedia

    INDEX
    Explanations

    occupation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     attacks
    -0.07
     practically
    -0.06
     lawyers
    -0.06
     Warning
    -0.06
     نق
    -0.06
    ivalent
    -0.06
     counterpart
    -0.06
     Village
    -0.06
     growth
    -0.06
    eworld
    -0.06
    POSITIVE LOGITS
    taskId
    0.07
     antennas
    0.06
    ogie
    0.06
    firstName
    0.06
    RAP
    0.06
    sessionId
    0.06
    simd
    0.06
     прог
    0.06
     helicopt
    0.06
    dateTime
    0.06
    Act Density 0.024%

    No Known Activations