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

    Neuronpedia

    INDEX
    Explanations

    Scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     valueType
    -0.07
     Caller
    -0.07
    共同体
    -0.06
    -0.06
     nud
    -0.06
    Cert
    -0.06
    series
    -0.06
     lắng
    -0.06
     person
    -0.06
    .setUser
    -0.06
    POSITIVE LOGITS
     Cannes
    0.09
    回报
    0.09
    zos
    0.08
     legion
    0.08
    pción
    0.07
     penetration
    0.07
    价值
    0.07
     desirable
    0.07
     upkeep
    0.07
    시키
    0.07
    Act Density 0.083%

    No Known Activations