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

    Neuronpedia

    INDEX
    Explanations

    crucial part or step

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     вариант
    0.94
    suitable
    0.91
     sytu
    0.90
    possible
    0.90
    scenario
    0.89
     가능한
    0.89
    Alternatively
    0.88
    preferred
    0.86
     варианты
    0.86
     preferable
    0.86
    POSITIVE LOGITS
     part
    1.65
     component
    1.55
     components
    1.48
     element
    1.42
     parts
    1.37
     ingredient
    1.36
     onderdeel
    1.34
     ingredients
    1.27
     Component
    1.26
     aspect
    1.25
    Act Density 0.402%

    No Known Activations