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

    Neuronpedia

    INDEX
    Explanations

    Math problems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sowohl
    -0.08
    уса
    -0.08
    igm
    -0.08
    .):
    -0.08
     ehemal
    -0.08
    kob
    -0.08
    )：
    -0.08
     maneh
    -0.07
     zarówno
    -0.07
     zwa
    -0.07
    POSITIVE LOGITS
     begins
    0.11
     starts
    0.11
     начинается
    0.10
     शुरुआत
    0.10
     commencer
    0.10
     ஆரம்ப
    0.10
     beginnt
    0.10
     börjar
    0.09
     başlam
    0.09
     börja
    0.09
    Act Density 0.124%

    No Known Activations