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

    Neuronpedia

    INDEX
    Explanations

    total

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    新闻
    -0.09
    自在
    -0.08
     সংবাদ
    -0.08
     playing
    -0.08
    逸
    -0.08
    uksia
    -0.08
    ニュース
    -0.07
     cwd
    -0.07
     Agree
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     requirements
    0.13
     요구
    0.13
    Requirements
    0.13
     demands
    0.13
     kebutuhan
    0.12
     Requirements
    0.12
    requirements
    0.12
     exigences
    0.12
     chọrọ
    0.12
     necesidades
    0.12
    Act Density 0.064%

    No Known Activations