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

    Neuronpedia

    INDEX
    Explanations

    efficiency, provision, prevention, exploration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Iterations
    0.45
    amentos
    0.44
    तया
    0.43
    tena
    0.42
     teoria
    0.41
    izador
    0.41
    Emails
    0.41
    taus
    0.41
     oiseaux
    0.41
    報
    0.41
    POSITIVE LOGITS
     catchy
    0.50
     costly
    0.46
     rapid
    0.43
     rift
    0.43
     holiday
    0.42
     findings
    0.41
     oversight
    0.41
     foreign
    0.41
     faster
    0.41
     impactful
    0.41
    Act Density 0.000%

    No Known Activations