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

    Neuronpedia

    INDEX
    Explanations

    astronomer Jack Hills

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Spitz
    0.39
    feri
    0.39
    Title
    0.39
     Goog
    0.39
     physic
    0.38
    Dee
    0.38
    Leaders
    0.38
    Bu
    0.38
    Fetch
    0.37
    Brend
    0.37
    POSITIVE LOGITS
     inorganic
    0.43
     enlist
    0.40
     leta
    0.39
     Ort
    0.37
     tahun
    0.36
     copyright
    0.36
     OR
    0.35
     enzymatic
    0.35
    salt
    0.35
    тку
    0.35
    Act Density 0.002%

    No Known Activations