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

    Neuronpedia

    INDEX
    Explanations

    soft robotic jellyfish

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cleanser
    0.41
     measurements
    0.38
     Mindfulness
    0.38
     speculation
    0.38
     calculations
    0.38
     blond
    0.38
     mindfulness
    0.38
     approximates
    0.38
     turner
    0.37
     formulas
    0.37
    POSITIVE LOGITS
     Retire
    0.45
    Pension
    0.45
    carbon
    0.44
     retire
    0.44
     Cas
    0.44
     cash
    0.41
     Carbon
    0.41
    Solar
    0.40
    退休
    0.40
    Carbon
    0.40
    Act Density 0.000%

    No Known Activations