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

    Neuronpedia

    INDEX
    Explanations

    code defines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aspiring
    -0.07
    ]+'
    -0.07
    usto
    -0.07
    Trait
    -0.07
    ช
    -0.06
     Mine
    -0.06
    ался
    -0.06
     RCC
    -0.06
    ]+"
    -0.06
    腦
    -0.06
    POSITIVE LOGITS
     fiercely
    0.06
     strikes
    0.06
     acceptance
    0.06
     engr
    0.06
     مهر
    0.06
    .sendFile
    0.06
    EM
    0.06
     پذیر
    0.06
     peeled
    0.06
    Monthly
    0.05
    Act Density 0.009%

    No Known Activations