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

    Neuronpedia

    INDEX
    Explanations

    estonian place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     それ
    0.90
     fallout
    0.88
     defer
    0.87
     muchas
    0.86
     halfway
    0.86
     largely
    0.85
     chen
    0.85
     uns
    0.84
     consonant
    0.84
     Imagine
    0.84
    POSITIVE LOGITS
     või
    1.34
     võ
    1.25
     töö
    1.24
    atsioon
    1.21
     mõ
    1.18
     rõ
    1.17
     kasut
    1.17
     põ
    1.16
     tä
    1.15
    õ
    1.14
    Act Density 0.004%

    No Known Activations