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

    Neuronpedia

    INDEX
    Explanations

    direction and location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Declared
    0.45
    StartY
    0.41
    AfterTax
    0.41
    OffsetY
    0.38
    YY
    0.38
     اسرائی
    0.38
    確か
    0.38
    Settl
    0.38
    WaitGroup
    0.37
     регули
    0.37
    POSITIVE LOGITS
    meros
    0.45
    ható
    0.42
     подобные
    0.42
     où
    0.42
     semelhantes
    0.42
    ión
    0.41
     Hinweise
    0.41
     similar
    0.40
     saúde
    0.40
    scratch
    0.40
    Act Density 37.718%

    No Known Activations