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

    Neuronpedia

    INDEX
    Explanations

    names, numbers, computer terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     लेखक
    1.08
     Founder
    1.06
     Homes
    1.06
     screenwriter
    1.05
    網友
    1.04
     ООО
    1.02
     Credit
    1.00
     ⋅
    0.99
     netizens
    0.98
     ©
    0.98
    POSITIVE LOGITS
    view
    0.82
     view
    0.75
    ask
    0.67
     ask
    0.66
     하면서
    0.65
    read
    0.64
    num
    0.62
    <h3>
    0.62
    View
    0.61
     numerically
    0.61
    Act Density 0.001%

    No Known Activations