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

    Neuronpedia

    INDEX
    Explanations

    organization, Babies, or math terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    insen
    0.47
    isin
    0.42
    ማሪ
    0.41
     gro
    0.41
     TP
    0.39
     tra
    0.38
     dessen
    0.37
     repe
    0.37
     Immediate
    0.36
     Stark
    0.36
    POSITIVE LOGITS
    信頼
    0.45
    بیر
    0.45
    Ship
    0.43
    Roberts
    0.43
     प्रदर्शन
    0.41
    ）
    0.39
    ඡ
    0.39
    Bag
    0.38
    ！）
    0.38
    ocular
    0.38
    Act Density 0.000%

    No Known Activations