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

    Neuronpedia

    INDEX
    Explanations

    explain a problem

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Date
    0.44
     object
    0.43
     earlier
    0.42
     Early
    0.41
     early
    0.41
     ETA
    0.41
    :
    0.40
     people
    0.40
    utu
    0.40
     IND
    0.40
    POSITIVE LOGITS
    ंधरा
    0.46
    Located
    0.43
    ︽
    0.43
    Situated
    0.42
     appartiennent
    0.42
    中美
    0.42
    letak
    0.41
    ︿
    0.41
     بیٹھ
    0.41
     лежит
    0.41
    Act Density 0.000%

    No Known Activations