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

    Neuronpedia

    INDEX
    Explanations

    ag followed by specific suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hler
    -0.89
    更に
    -0.84
    ół
    -0.82
     further
    -0.81
    どうやら
    -0.80
    therosclerosis
    -0.78
    mahami
    -0.77
     Satt
    -0.75
    FURTHER
    -0.75
     furthermore
    -0.75
    POSITIVE LOGITS
     Ag
    1.45
     ag
    1.37
    Ag
    1.32
     AG
    1.13
     Agn
    1.01
    这些
    0.92
     AGR
    0.89
     Agenda
    0.87
    Agenda
    0.85
    Aging
    0.85
    Act Density 0.056%

    No Known Activations