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

    Neuronpedia

    INDEX
    Explanations

    philosophical terms and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ribbon
    0.74
    }(-
    0.73
     Educators
    0.70
     topLine
    0.68
     congregate
    0.66
     Imani
    0.66
     JUN
    0.66
    voli
    0.66
     kroz
    0.66
    िंक
    0.65
    POSITIVE LOGITS
     dox
    1.01
     entail
    0.94
    criptions
    0.92
    Modal
    0.88
     philosophers
    0.87
     দার্শন
    0.87
     explan
    0.86
     elimin
    0.86
    SEP
    0.86
    rightsquigarrow
    0.85
    Act Density 0.230%

    No Known Activations