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

    Neuronpedia

    INDEX
    Explanations

    Common English language filler

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     billion
    -0.07
    -government
    -0.07
    Driven
    -0.07
     Difficulty
    -0.07
     supervisor
    -0.07
    нт
    -0.07
     pressure
    -0.06
     Template
    -0.06
     Fletcher
    -0.06
    ест
    -0.06
    POSITIVE LOGITS
    雅黑
    0.07
     Blow
    0.06
     kop
    0.06
    老
    0.06
    .bindingNavigatorMove
    0.06
     earthqu
    0.06
    ,axis
    0.06
    ….
    0.05
    ะแ
    0.05
    ']))
↵
    0.05
    Act Density 0.264%

    No Known Activations