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

    Neuronpedia

    INDEX
    Explanations

    6 people, inherent worth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bring
    0.38
     table
    0.36
     Pres
    0.36
     actu
    0.35
    past
    0.35
     past
    0.35
    δ
    0.35
    table
    0.34
     fu
    0.34
    தில்
    0.34
    POSITIVE LOGITS
     സോഷ്യ
    0.42
     syukur
    0.40
     leveraged
    0.40
    ्सा
    0.40
    과학
    0.38
    esters
    0.38
    𝚢
    0.38
    盐
    0.37
    yukur
    0.37
     বিপ
    0.37
    Act Density 0.000%

    No Known Activations