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

    Neuronpedia

    INDEX
    Explanations

    Okay, I understand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     LDL
    0.70
     आहार
    0.70
     SOA
    0.70
     Style
    0.66
     style
    0.64
    style
    0.63
    Compute
    0.63
     spectrophot
    0.61
    ण्
    0.61
    ∙
    0.61
    POSITIVE LOGITS
     aastal
    0.78
     సీఎం
    0.76
     funcionarios
    0.75
    フロント
    0.75
     চূড়ান্ত
    0.74
     Потому
    0.73
    ในสนาม
    0.73
    掮
    0.72
     Axios
    0.72
     ಕಾಂಗ್ರೆ
    0.72
    Act Density 0.332%

    No Known Activations