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

    Neuronpedia

    INDEX
    Explanations

    constructors and getters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nedostat
    0.41
     कण
    0.40
    Lad
    0.40
    ហើយ
    0.37
    ழ்
    0.37
    hul
    0.37
    Plastic
    0.37
     overd
    0.36
     bolsas
    0.36
    ፍ
    0.36
    POSITIVE LOGITS
    scal
    0.39
     wohl
    0.35
    requireNonNull
    0.35
    itivity
    0.33
    getattr
    0.33
    sov
    0.32
    soe
    0.32
    สิ้น
    0.32
     vardı
    0.32
     исполни
    0.32
    Act Density 0.001%

    No Known Activations