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

    Neuronpedia

    INDEX
    Explanations

    references to weight and heaviness in objects

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

    weight and associated units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    andoah
    -0.44
     otomatis
    -0.38
    OwnProperty
    -0.37
    closePath
    -0.36
    moveToNext
    -0.36
    ligators
    -0.35
     Paglinawan
    -0.35
     thither
    -0.35
     Inv
    -0.35
    GroupLayout
    -0.34
    POSITIVE LOGITS
     weight
    0.97
    weight
    0.89
     weights
    0.88
     weighing
    0.82
    Weight
    0.82
     Weight
    0.80
     Gewichts
    0.79
     heavier
    0.77
     weigh
    0.76
    weigh
    0.76
    Act Density 0.086%

    No Known Activations