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

    Neuronpedia

    INDEX
    Explanations

    offering further help or options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IAM
    0.97
    coln
    0.96
    AUC
    0.91
    ricorn
    0.90
    یتی
    0.89
    \\
    0.87
    ায়ত্ত
    0.86
     Existen
    0.85
    estries
    0.85
    ezi
    0.85
    POSITIVE LOGITS
    oretically
    1.78
    ங்கிணை
    1.57
    orems
    1.53
     Wikiseite
    1.22
    weds
    1.18
    ઉસ
    1.16
     вариант
    1.05
     apologize
    1.04
    に変更
    1.02
    koliko
    1.01
    Act Density 0.745%

    No Known Activations