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

    Neuronpedia

    INDEX
    Explanations

    programming language syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     metabolized
    0.31
    HUS
    0.29
    Miller
    0.29
     Gloucester
    0.29
    Anderson
    0.29
    শরীর
    0.28
     macromolecules
    0.28
    Water
    0.28
    soluble
    0.27
     water
    0.27
    POSITIVE LOGITS
    ，
    0.31
    ３
    0.30
    ྥ
    0.30
    િટ
    0.30
    １
    0.29
    が必要です
    0.29
     ო
    0.29
     होगा
    0.28
    ր
    0.28
    ሪያ
    0.28
    Act Density 0.449%

    No Known Activations