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

    Neuronpedia

    INDEX
    Explanations

    defendant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Marriage
    -0.07
    ruz
    -0.07
     silently
    -0.06
    oration
    -0.06
    았
    -0.06
     evacuation
    -0.06
    еления
    -0.06
    هور
    -0.06
    -t
    -0.06
     Swiss
    -0.06
    POSITIVE LOGITS
     raft
    0.06
     Lesb
    0.06
     Registers
    0.06
     OpCode
    0.06
    ुपए
    0.06
     Civic
    0.06
     Decoder
    0.06
    대학
    0.06
     totalTime
    0.06
    0.06
    Act Density 0.014%

    No Known Activations