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

    Neuronpedia

    INDEX
    Explanations

    definitions and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     laziness
    0.29
     eigenfunctions
    0.29
     synt
    0.29
     corre
    0.29
     calcS
    0.29
     rares
    0.28
     makna
    0.28
     taxas
    0.28
     correctes
    0.28
     horizont
    0.28
    POSITIVE LOGITS
    ervice
    0.32
    <unused209>
    0.31
    <unused745>
    0.31
    org
    0.30
     When
    0.30
     Today
    0.30
    oris
    0.30
    <unused689>
    0.30
    <unused415>
    0.29
    <unused2130>
    0.29
    Act Density 0.231%

    No Known Activations