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

    Neuronpedia

    INDEX
    Explanations

    at least

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    imer
    0.34
    ieren
    0.33
    eteers
    0.33
    స్తారు
    0.32
    ieux
    0.31
     kolem
    0.31
    ம்தான்
    0.31
    ':'
    0.31
    ]$-
    0.31
    산을
    0.30
    POSITIVE LOGITS
     least
    3.13
    Least
    2.81
    least
    2.80
     Least
    2.78
    至少
    2.73
     najman
    2.63
     حداقل
    2.63
     almeno
    2.50
     최소
    2.42
    少なくとも
    2.42
    Act Density 0.024%

    No Known Activations