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

    Neuronpedia

    INDEX
    Explanations

    the [noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ర్థిక
    0.35
    ^{+}
    0.34
     eurozone
    0.33
    %;
    0.31
     δύο
    0.31
     వారు
    0.31
    iselt
    0.30
    ével
    0.30
     この
    0.30
     Lesotho
    0.30
    POSITIVE LOGITS
    น
    0.38
    ن
    0.37
    с
    0.37
    س
    0.37
    RO
    0.35
    s
    0.34
    p
    0.34
    .
    0.33
    ↵
    0.33
    מ
    0.33
    Act Density 0.061%

    No Known Activations