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

    Neuronpedia

    INDEX
    Explanations

    domain topic contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鶘
    0.41
     ponctuées
    0.40
    厉害
    0.38
    嚏
    0.38
    hearts
    0.38
    𝐳
    0.38
    եր
    0.37
    zos
    0.37
     taxpayer
    0.37
     노력
    0.36
    POSITIVE LOGITS
     ಸಾಮಾನ್ಯವಾಗಿ
    0.45
     Installations
    0.45
     Mainly
    0.44
     Commonly
    0.44
     urban
    0.42
     Introdu
    0.41
     projects
    0.41
    │
    0.41
     mainly
    0.40
    蔺
    0.40
    Act Density 0.021%

    No Known Activations