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

    Neuronpedia

    INDEX
    Explanations

    programming control flow keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {
    0.44
    BASE
    0.43
    ()
    0.41
    6
    0.38
     panoram
    0.38
    March
    0.37
    HAT
    0.37
    3
    0.37
    ្វី
    0.36
    화를
    0.36
    POSITIVE LOGITS
    تی
    0.38
     বোন
    0.36
    innis
    0.36
     және
    0.34
    andt
    0.34
    kowe
    0.34
    knings
    0.34
    عکس
    0.34
    kinetic
    0.34
    Დ
    0.34
    Act Density 0.100%

    No Known Activations