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

    Neuronpedia

    INDEX
    Explanations

    defining outcomes instead of process

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Factors
    -0.09
    Factors
    -0.09
     Faktoren
    -0.08
     factoren
    -0.08
    尸
    -0.08
    因素
    -0.07
     Subscribers
    -0.07
    之前
    -0.07
     Caribe
    -0.07
     retra
    -0.07
    POSITIVE LOGITS
     broad
    0.09
    abstract
    0.09
     abstract
    0.09
     outcome
    0.09
     specifying
    0.09
     üld
    0.09
     ulaş
    0.08
     appellate
    0.08
     flexible
    0.08
    Desired
    0.08
    Act Density 0.029%

    No Known Activations