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

    Neuronpedia

    INDEX
    Explanations

    fits or adaptable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     politici
    0.56
     prostit
    0.54
     discredit
    0.52
     politische
    0.51
     politik
    0.50
     guerras
    0.49
     politiques
    0.47
     billionaires
    0.47
     stratégies
    0.46
     anúncios
    0.46
    POSITIVE LOGITS
     adjustable
    0.68
     Compatible
    0.66
    adjustable
    0.64
     compatible
    0.63
     customizable
    0.63
     versatile
    0.62
     adaptable
    0.61
     подходит
    0.61
     Adjustable
    0.60
     durable
    0.59
    Act Density 0.067%

    No Known Activations