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

    Neuronpedia

    INDEX
    Explanations

    country names and data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ید
    0.54
     φω
    0.54
     रासायनिक
    0.46
     mää
    0.45
    腕時計
    0.45
    ATIVE
    0.44
    県の
    0.44
     wat
    0.43
    icyclic
    0.43
    เร็ว
    0.43
    POSITIVE LOGITS
     Realtors
    0.40
    В
    0.40
    丁
    0.40
    СТО
    0.39
    Рус
    0.38
    жали
    0.38
    SKY
    0.38
     أق
    0.38
     SCRE
    0.37
     organizations
    0.37
    Act Density 0.000%

    No Known Activations