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

    Neuronpedia

    INDEX
    Explanations

    say "business" word

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mistress
    -0.07
    ره
    -0.06
     où
    -0.06
    เตอร
    -0.06
    }".
    -0.06
    ري
    -0.06
    лан
    -0.06
     서비스
    -0.06
     vscode
    -0.06
    اري
    -0.06
    POSITIVE LOGITS
     katı
    0.07
     اص
    0.07
    ollah
    0.06
    ategory
    0.06
    (locale
    0.06
     ;)↵↵
    0.06
    _um
    0.06
     اعتماد
    0.06
     hak
    0.06
     milliseconds
    0.06
    Act Density 0.044%

    No Known Activations