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

    Neuronpedia

    INDEX
    Explanations

    words inside markdown asterisks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \"
    0.26
    description
    0.23
    Descripción
    0.23
     instructions
    0.23
    \:
    0.23
    矨
    0.23
    📝
    0.22
    \".
    0.22
    Description
    0.22
    ค่า
    0.22
    POSITIVE LOGITS
     K
    0.42
     H
    0.37
     J
    0.37
     Z
    0.36
     B
    0.36
     V
    0.35
     N
    0.35
     G
    0.35
     R
    0.34
     T
    0.34
    Act Density 0.173%

    No Known Activations