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

    Neuronpedia

    INDEX
    Explanations

    Independence, balance, context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Carbon
    0.59
    А
    0.50
    <0x0D>
    0.46
    ופ
    0.46
    Heavy
    0.46
    Vehicle
    0.45
    Gesch
    0.44
    洹
    0.44
    Inventory
    0.44
    uuml
    0.43
    POSITIVE LOGITS
     proviso
    0.55
     poverty
    0.52
     prevalent
    0.52
     prevalence
    0.51
     postpartum
    0.51
     primero
    0.50
     exuber
    0.50
     streetwear
    0.49
     pirm
    0.48
     poursuivre
    0.48
    Act Density 0.009%

    No Known Activations