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

    Neuronpedia

    INDEX
    Explanations

    restrict foreign

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    資
    0.45
     филосо
    0.45
    第一個
    0.43
    selValue
    0.42
     आफ्नो
    0.42
    特斯拉
    0.41
     Aging
    0.41
     emberek
    0.40
     てる
    0.40
     Blogging
    0.40
    POSITIVE LOGITS
    ṟ
    0.50
     deten
    0.48
     roz
    0.48
    ης
    0.47
     warmly
    0.47
    lx
    0.46
    টি
    0.45
    там
    0.45
     detention
    0.45
    RP
    0.44
    Act Density 0.000%

    No Known Activations