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

    Neuronpedia

    INDEX
    Explanations

    fit, unfit, or medical status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ദുൽ
    0.41
    輩
    0.39
    ónico
    0.38
     एडज
    0.38
     Natalie
    0.38
     inseparable
    0.37
    Natalie
    0.37
    琹
    0.37
     clique
    0.36
    Normal
    0.36
    POSITIVE LOGITS
     fitness
    1.42
     fit
    1.39
    Fitness
    1.38
    fitness
    1.36
     unfit
    1.34
     Fitness
    1.32
     Fit
    1.26
    Fit
    1.23
     FITNESS
    1.19
    fit
    1.16
    Act Density 0.012%

    No Known Activations