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

    Neuronpedia

    INDEX
    Explanations

    finding max, min, unique values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     मार्शल
    0.40
     사인
    0.39
    opharmaceuticals
    0.38
    andan
    0.38
    ricane
    0.37
    制造业
    0.36
     रहें
    0.35
     সহযোগ
    0.35
    ایید
    0.35
    诞
    0.35
    POSITIVE LOGITS
     max
    1.32
    max
    1.20
     Max
    1.01
     min
    0.99
    Max
    0.96
     MAX
    0.89
     máxim
    0.89
    min
    0.86
    MAX
    0.86
     maximum
    0.86
    Act Density 0.017%

    No Known Activations