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

    Neuronpedia

    INDEX
    Explanations

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     peanuts
    0.40
    ｄ
    0.38
     neutrophils
    0.38
    няется
    0.37
     cornice
    0.36
    Href
    0.36
     glycoproteins
    0.36
     glycoprotein
    0.35
     архівної
    0.35
     timeliness
    0.35
    POSITIVE LOGITS
     १५
    0.43
    5
    0.43
     ১৫
    0.43
     Buzz
    0.43
     Intensity
    0.42
     ausges
    0.41
     ۱۵
    0.40
     ۵
    0.40
    Template
    0.39
     millón
    0.39
    Act Density 0.002%

    No Known Activations