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

    Neuronpedia

    INDEX
    Explanations

    concepts and language related to change or transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    things changing or shifting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.53
     ervan
    -0.48
    sembly
    -0.46
    contri
    -0.45
     estekak
    -0.41
     biß
    -0.41
    efty
    -0.41
     חיצוניים
    -0.40
     Meksiku
    -0.40
     Summe
    -0.40
    POSITIVE LOGITS
     changed
    0.63
     changer
    0.59
     change
    0.56
     changing
    0.52
    change
    0.51
    CHANGE
    0.50
     cambiar
    0.49
     измени
    0.49
     changé
    0.48
     CHANGE
    0.48
    Act Density 0.040%

    No Known Activations