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

    Neuronpedia

    INDEX
    Explanations

    GPT sites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সংগ্রহ
    0.39
    ScrollView
    0.36
    Agriculture
    0.36
     schweren
    0.36
    unité
    0.36
     sequentially
    0.35
    Télé
    0.35
     प्रतिनिधित्व
    0.34
     Євро
    0.34
    adobe
    0.34
    POSITIVE LOGITS
     Musk
    0.42
    <0xBA>
    0.41
    личие
    0.40
    চ্ছে
    0.38
     thefe
    0.38
    bro
    0.38
    atus
    0.38
    fek
    0.38
     betekent
    0.37
     diferente
    0.37
    Act Density 0.001%

    No Known Activations