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

    Neuronpedia

    INDEX
    Explanations

    general knowledge and guidance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تتم
    0.79
     does
    0.77
     sót
    0.76
    posium
    0.76
     अधिका
    0.75
     Specify
    0.74
     Faculté
    0.74
     ilişkin
    0.74
    頫
    0.72
     leçon
    0.72
    POSITIVE LOGITS
     general
    1.32
    General
    1.22
     General
    1.20
    general
    1.10
     generic
    1.03
     generalized
    1.01
     GENERAL
    0.99
     जनरल
    0.95
    generic
    0.95
    GENERAL
    0.92
    Act Density 0.015%

    No Known Activations