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

    Neuronpedia

    INDEX
    Explanations

    web requests and firewalls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     শ্বাস
    0.41
    自治
    0.41
     autón
    0.40
     autonomía
    0.40
    認証
    0.39
     uitz
    0.39
     Austen
    0.39
     autonomy
    0.38
    構成
    0.38
     Autonomous
    0.38
    POSITIVE LOGITS
    හෙ
    0.42
     builders
    0.42
     firewall
    0.41
     builder
    0.41
    Builders
    0.39
    Trans
    0.37
     Bayer
    0.37
    ёма
    0.36
    builders
    0.36
    Executive
    0.36
    Act Density 0.000%

    No Known Activations