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

    Neuronpedia

    INDEX
    Explanations

    schema types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     imagined
    0.45
     envision
    0.42
    నించ
    0.40
     envisioned
    0.40
     provocative
    0.39
     imagining
    0.39
     imaginary
    0.39
    ያዎች
    0.39
     provoking
    0.38
     Константи
    0.38
    POSITIVE LOGITS
    amaz
    0.40
    assist
    0.39
     get
    0.38
    wasm
    0.38
    str
    0.37
    市
    0.37
    まで
    0.37
     Management
    0.36
    Amaz
    0.36
     again
    0.36
    Act Density 0.001%

    No Known Activations