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

    Neuronpedia

    INDEX
    Explanations

    levelname

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tx
    -0.07
    ddl
    -0.07
     playa
    -0.07
    noloj
    -0.07
    asics
    -0.07
     proč
    -0.06
     Gorgeous
    -0.06
     удоб
    -0.06
    .googleapis
    -0.06
    female
    -0.06
    POSITIVE LOGITS
     direction
    0.06
    心里
    0.06
     пери
    0.06
     मन
    0.06
    [level
    0.06
     pressures
    0.06
     relaxing
    0.06
    من
    0.06
     María
    0.06
     "\
    0.06
    Act Density 0.004%

    No Known Activations