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

    Neuronpedia

    INDEX
    Explanations

    command-line interface

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Models
    -0.08
     Вел
    -0.08
    .Models
    -0.07
     indulg
    -0.07
    Inner
    -0.07
    éd
    -0.07
     petty
    -0.07
    .Relative
    -0.07
     fres
    -0.07
    engin
    -0.07
    POSITIVE LOGITS
     automation
    0.15
     automate
    0.14
     automatis
    0.14
     automat
    0.14
    automation
    0.14
     자동
    0.13
     автомат
    0.13
     Automation
    0.13
    Automation
    0.13
     Automat
    0.12
    Act Density 0.036%

    No Known Activations