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

    Neuronpedia

    INDEX
    Explanations

    ctest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    尊
    -0.07
     Equality
    -0.07
    这个
    -0.07
     Authority
    -0.07
     wart
    -0.07
     ánh
    -0.07
    VarInsn
    -0.07
    итет
    -0.07
     Woodward
    -0.06
    ORITY
    -0.06
    POSITIVE LOGITS
     agile
    0.06
     �
    0.06
     م
    0.06
     Strategic
    0.05
    _INIT
    0.05
     Generic
    0.05
     konnte
    0.05
    Memory
    0.05
    _class
    0.05
     ignite
    0.05
    Act Density 0.000%

    No Known Activations