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

    Neuronpedia

    INDEX
    Explanations

    object instantiation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     covariates
    0.87
     ponder
    0.86
     песни
    0.80
     codons
    0.80
     strtotime
    0.74
     covariate
    0.72
     aldehydes
    0.70
     payloads
    0.70
     paintings
    0.70
    Dockerfile
    0.70
    POSITIVE LOGITS
     экзем
    1.46
    instance
    1.34
    实例
    1.34
    实例化
    1.34
    Instance
    1.23
     instance
    1.23
     instancia
    1.22
     getInstance
    1.14
     Instances
    1.13
    getInstance
    1.13
    Act Density 0.996%

    No Known Activations