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

    Neuronpedia

    INDEX
    Explanations

    memory allocation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aigu
    0.50
     assigning
    0.50
     assign
    0.49
     assegn
    0.46
    assigned
    0.46
     assigned
    0.46
     ሀ
    0.46
     appointing
    0.45
     randomly
    0.44
     meticulously
    0.44
    POSITIVE LOGITS
    0
    0.45
    Resol
    0.42
    CHAPTER
    0.42
     transistor
    0.41
     Quil
    0.40
    Grav
    0.40
    ution
    0.40
    समय
    0.39
    chapters
    0.39
     Chav
    0.38
    Act Density 0.005%

    No Known Activations