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

    Neuronpedia

    INDEX
    Explanations

    Tibetan lama

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     endpoint
    0.43
    ک
    0.42
     errore
    0.41
    jana
    0.39
     O
    0.39
     о
    0.38
    gest
    0.38
    łach
    0.38
    !}
    0.37
     SOUND
    0.37
    POSITIVE LOGITS
    琦
    0.39
     suaves
    0.39
    履行
    0.38
     swat
    0.38
    南京
    0.38
    щины
    0.37
     corporal
    0.37
     diabetics
    0.37
     것은
    0.36
     계획
    0.35
    Act Density 0.001%

    No Known Activations