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

    Neuronpedia

    INDEX
    Explanations

    transition and state change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     थीं
    1.49
     были
    1.25
     weren
    1.20
     थे
    1.19
     ήταν
    1.18
     تھے
    1.17
    Were
    1.17
    were
    1.16
     były
    1.14
     були
    1.12
    POSITIVE LOGITS
     goes
    3.34
     begins
    3.28
     enters
    3.19
     becomes
    3.06
     gets
    3.04
     disappears
    3.03
     ensues
    2.88
     occurs
    2.88
     grows
    2.87
     comes
    2.87
    Act Density 0.438%

    No Known Activations