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

    Neuronpedia

    INDEX
    Explanations

    Starting sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    أشي
    -0.08
    さん
    -0.07
    _positive
    -0.07
     Pension
    -0.07
    峱
    -0.07
    @Bean
    -0.07
    地带
    -0.07
    电线
    -0.07
    경영
    -0.07
    招收
    -0.07
    POSITIVE LOGITS
    忧
    0.07
     alleg
    0.07
     Design
    0.07
    	init
    0.06
    _overlap
    0.06
     sqrt
    0.06
     la
    0.06
     idi
    0.06
     off
    0.06
    titles
    0.06
    Act Density 0.115%

    No Known Activations