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

    Neuronpedia

    INDEX
    Explanations

    technical and procedural contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Botan
    0.45
     botany
    0.44
     डिट
    0.41
    Archae
    0.40
     botan
    0.40
    BOOT
    0.40
    plants
    0.39
    Burn
    0.39
     Botany
    0.39
    Museum
    0.38
    POSITIVE LOGITS
     driven
    0.43
     milhões
    0.40
     урав
    0.40
    âmara
    0.39
     incum
    0.38
     Ler
    0.38
    쳥
    0.38
     अतिक
    0.37
     блока
    0.37
     drove
    0.37
    Act Density 0.000%

    No Known Activations