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

    Neuronpedia

    INDEX
    Explanations

    memory context or libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    කාශ
    0.52
    ánicos
    0.42
    ющими
    0.41
    ografica
    0.40
    ikki
    0.39
     ремонта
    0.39
    нар
    0.39
     පැ
    0.39
    prem
    0.38
    sprech
    0.38
    POSITIVE LOGITS
    緝
    0.48
    I
    0.47
     I
    0.46
    )})
    0.46
    Iterable
    0.46
    وست
    0.45
    סט
    0.44
     SIL
    0.44
     traditionnel
    0.44
     الإ
    0.44
    Act Density 0.000%

    No Known Activations