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

    Neuronpedia

    INDEX
    Explanations

    make or making something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    4
    0.38
    2
    0.36
    5
    0.35
    6
    0.33
    when
    0.31
    0
    0.31
    І
    0.30
    า
    0.30
    ।
    0.29
     vremena
    0.29
    POSITIVE LOGITS
     sure
    0.43
     it
    0.39
     amends
    0.36
     make
    0.36
     decisions
    0.34
     up
    0.32
    hift
    0.31
     headlines
    0.29
     everything
    0.29
    ه
    0.29
    Act Density 0.083%

    No Known Activations